Open Access. Powered by Scholars. Published by Universities.®

Programming Languages and Compilers Commons™

Open Access. Powered by Scholars. Published by Universities.®

Research Collection School Of Computing and Information Systems

Discipline
Keyword
Publication Year

Articles 61 - 90 of 379

Full-Text Articles in Programming Languages and Compilers

Enhancing Llm-Based Coding Tools Through Native Integration Of Ide-Derived Static Context, Yichen Li, Yun Peng, Yintong Huo, R. Michael Lyu Apr 2025

Enhancing Llm-Based Coding Tools Through Native Integration Of Ide-Derived Static Context, Yichen Li, Yun Peng, Yintong Huo, R. Michael Lyu

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have achieved remarkable success in code completion, as evidenced by their essential roles in developing code assistant services such as Copilot. Being trained on in-file contexts, current LLMs are quite effective in completing code for single source files. However, it is challenging for them to conduct repository-level code completion for large software projects that require cross-file information. Existing research on LLM-based repository-level code completion identifies and integrates cross-file contexts, but it suffers from low accuracy and limited context length of LLMs. In this paper, we argue that Integrated Development Environments (IDEs) can provide direct, accurate and …

Go to article

Bootstrapping Language Models With Dpo Implicit Rewards, Changyu Chen, Zichen Liu, Chao Du, Tianyu Pang, Qian Liu, Arunesh Sinha, Pradeep Varakantham, Min Lin Apr 2025

Bootstrapping Language Models With Dpo Implicit Rewards, Changyu Chen, Zichen Liu, Chao Du, Tianyu Pang, Qian Liu, Arunesh Sinha, Pradeep Varakantham, Min Lin

Research Collection School Of Computing and Information Systems

Human alignment in large language models (LLMs) is an active area of research. A recent groundbreaking work, direct preference optimization (DPO), has greatly simplified the process from past work in reinforcement learning from human feedback (RLHF) by bypassing the reward learning stage in RLHF. DPO, after training, provides an implicit reward model. In this work, we make a novel observation that this implicit reward model can by itself be used in a bootstrapping fashion to further align the LLM. Our approach is to use the rewards from a current LLM model to construct a preference dataset, which is then used …

Go to article

Birdie: Natural Language-Driven Table Discovery Using Differentiable Search Index, Yuxiang Guo, Zhonghao Hu, Yuren Mao, Baihua Zheng, Yunjun Gao, Mingwei Zhou Mar 2025

Birdie: Natural Language-Driven Table Discovery Using Differentiable Search Index, Yuxiang Guo, Zhonghao Hu, Yuren Mao, Baihua Zheng, Yunjun Gao, Mingwei Zhou

Research Collection School Of Computing and Information Systems

Natural language (NL)-driven table discovery identifies relevant tables from large table repositories based on NL queries. While current deep-learning-based methods using the traditional dense vector search pipeline, i.e., representation-index-search, achieve remarkable accuracy, they face several limitations that impede further performance improvements: (i) the errors accumulated during the table representation and indexing phases affect the subsequent search accuracy; and (ii) insufficient query-table interaction hinders effective semantic alignment, impeding accuracy improvements. In this paper, we propose a novel framework Birdie, using a differentiate search index. It unifies the indexing and search into a single encoder-decoder language model, thus getting rid of error …

Go to article

Attackg+: Boosting Attack Graph Construction With Large Language Models, Yongheng Zhang, Tingwen Du, Yunshan Ma, Xiang Wang, Yi Xie, Guozheng Yang, Yuliang Lu, Ee‑Chien Chang Mar 2025

Attackg+: Boosting Attack Graph Construction With Large Language Models, Yongheng Zhang, Tingwen Du, Yunshan Ma, Xiang Wang, Yi Xie, Guozheng Yang, Yuliang Lu, Ee‑Chien Chang

Research Collection School Of Computing and Information Systems

Attack graph construction seeks to convert textual cyber threat intelligence (CTI) reports into structuredrepresentations, portraying the evolutionary traces of cyber attacks. Even though previous research hasproposed various methods to construct attack graphs, they generally suffer from limited generalizationcapability to diverse knowledge types as well as requirement of expertise in model design and tuning.Addressing these limitations, we seek to utilize Large Language Models (LLMs), which have achieved enormoussuccess in a broad range of tasks given exceptional capabilities in both language understanding and zeroshot task fulfillment. Thus, we propose a fully automatic LLM-based framework to construct attack graphsnamed: AttacKG+. Our framework consists …

Go to article

A Causality-Aware Paradigm For Evaluating Creativity Of Multimodal Large Language Models, Zhongzhan Huang, Shanshan Zhong, Pan Zhou, Shanghua Gao, Marink Zitnik, Liang Lin Feb 2025

A Causality-Aware Paradigm For Evaluating Creativity Of Multimodal Large Language Models, Zhongzhan Huang, Shanshan Zhong, Pan Zhou, Shanghua Gao, Marink Zitnik, Liang Lin

Research Collection School Of Computing and Information Systems

Recently, numerous benchmarks have been developed to evaluate the logical reasoning abilities of large language models (LLMs). However, assessing the equally important creative capabilities of LLMs is challenging due to the subjective, diverse, and data-scarce nature of creativity, especially in multimodal scenarios. In this paper, we consider the comprehensive pipeline for evaluating the creativity of multimodal LLMs, with a focus on suitable evaluation platforms and methodologies. First, we find the Oogiri game—a creativity-driven task requiring humor, associative thinking, and the ability to produce unexpected responses to text, images, or both. This game aligns well with the input-output structure of modern …

Go to article

Financial Named Entity Recognition: How Far Can Llm Go?, Yi-Te Lu, Yintong Huo Jan 2025

Financial Named Entity Recognition: How Far Can Llm Go?, Yi-Te Lu, Yintong Huo

Research Collection School Of Computing and Information Systems

The surge of large language models (LLMs) has revolutionized the extraction and analysis of crucial information from a growing volume of financial statements, announcements, and business news. Recognition for named entities to construct structured data poses a significant challenge in analyzing financial documents and is a foundational task for intelligent financial analytics. However, how effective are these generic LLMs and their performance under various prompts are yet need a better understanding. To fill in the blank, we present a systematic evaluation of state-of-the-art LLMs and prompting methods in the financial Named Entity Recognition (NER) problem. Specifically, our experimental results highlight …

Go to article

Reevo: Large Language Models As Hyper-Heuristics With Reflective Evolution, Haoran Ye, Jiarui Wang, Zhiguang Cao, Federico Berto, Chuanbo Hua, Haeyeon Kim, Jinkyoo Park, Guojie Song Dec 2024

Reevo: Large Language Models As Hyper-Heuristics With Reflective Evolution, Haoran Ye, Jiarui Wang, Zhiguang Cao, Federico Berto, Chuanbo Hua, Haeyeon Kim, Jinkyoo Park, Guojie Song

Research Collection School Of Computing and Information Systems

The omnipresence of NP-hard combinatorial optimization problems (COPs) compels domain experts to engage in trial-and-error heuristic design process. The long-standing endeavor of design automation has gained new momentum with the rise of large language models (LLMs). This paper introduces Language Hyper-Heuristics (LHHs), an emerging variant of Hyper-Heuristics that leverages LLMs for heuristic generation, featuring minimal manual intervention and open-ended heuristic spaces. To empower LHHs, we present Reflective Evolution (ReEvo), a generic searching framework that emulates the reflective design approach of human experts while far surpassing human capabilities with its scalable LLM inference, Internet-scale domain knowledge, and powerful evolutionary search. Evaluations …

Go to article

Revisiting Masked Auto-Encoders For Ecg-Language Representation Learning, Hung Manh Pham, Aaqib Saeed, Dong Ma Dec 2024

Revisiting Masked Auto-Encoders For Ecg-Language Representation Learning, Hung Manh Pham, Aaqib Saeed, Dong Ma

Research Collection School Of Computing and Information Systems

We propose C-MELT, a novel framework for multimodal self-supervised learning of Electrocardiogram (ECG) and text encoders. C-MELT pre-trains a contrastive-enhanced masked auto-encoder architecture using ECG-text paired data. It exploits the generative strengths with improved discriminative capabilities to enable robust cross-modal alignment. This is accomplished through a carefully designed model, loss functions, and a novel negative sampling strategy. Our preliminary experiments demonstrate significant performance improvements with up to 12% in downstream cardiac arrhythmia classification and patient identification tasks. Our findings demonstrate C-MELT's capacity to extract rich, clinically relevant features from ECG-text pairs, paving the way for more accurate and efficient cardiac …

Go to article

Divlog: Log Parsing With Prompt Enhanced In-Context Learning, Junjielong Xu, Ruichun Yang, Yintong Huo, Chengyu Zhang, Pinjia He Dec 2024

Divlog: Log Parsing With Prompt Enhanced In-Context Learning, Junjielong Xu, Ruichun Yang, Yintong Huo, Chengyu Zhang, Pinjia He

Research Collection School Of Computing and Information Systems

Log parsing, which involves log template extraction from semistructured logs to produce structured logs, is the first and the most critical step in automated log analysis. However, current log parsers suffer from limited effectiveness for two reasons. First, traditional data-driven log parsers solely rely on heuristics or handcrafted features designed by domain experts, which may not consistently perform well on logs from diverse systems. Second, existing supervised log parsers require model tuning, which is often limited to fixed training samples and causes sub-optimal performance across the entire log source. To address this limitation, we propose DivLog, an effective log parsing …

Go to article

Mm‑Forecast: A Multimodal Approach To Temporal Event Forecasting With Large Language Models, Haoxuan Li, Zhengmao Yang, Yunshan Ma, Yi Bin, Yang Yang, Tat-Seng Chua Nov 2024

Mm‑Forecast: A Multimodal Approach To Temporal Event Forecasting With Large Language Models, Haoxuan Li, Zhengmao Yang, Yunshan Ma, Yi Bin, Yang Yang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

We study an emerging and intriguing problem of multimodal temporal event forecasting with large language models. Compared to using text or graph modalities, the investigation of utilizing images for temporal event forecasting has not been fully explored, especially in the era of large language models (LLMs). To bridge this gap, we are particularly interested in two key questions of: 1) why images will help in temporal event forecasting, and 2) how to integrate images into the LLM-based forecasting framework. To answer these research questions, we propose to identify two essential functions that images play in the scenario of temporal event …

Go to article

Sound And Complete Witnesses For Template-Based Verification Of Ltl Properties On Polynomial Programs, Krishnendu Chatterjee, Amir Goharshady, Ehsan Goharshady, Mehrdad Karrabi, Dorde Zikelic Sep 2024

Sound And Complete Witnesses For Template-Based Verification Of Ltl Properties On Polynomial Programs, Krishnendu Chatterjee, Amir Goharshady, Ehsan Goharshady, Mehrdad Karrabi, Dorde Zikelic

Research Collection School Of Computing and Information Systems

We study the classical problem of verifying programs with respect to formal specifications given in the linear temporal logic (LTL). We first present novel sound and complete witnesses for LTL verification over imperative programs. Our witnesses are applicable to both verification (proving) and refutation (finding bugs) settings. We then consider LTL formulas in which atomic propositions can be polynomial constraints and turn our focus to polynomial arithmetic programs, i.e. programs in which every assignment and guard consists only of polynomial expressions. For this setting, we provide an efficient algorithm to automatically synthesize such LTL witnesses. Our synthesis procedure is both …

Go to article

Style: Improving Domain Transferability Of Asking Clarification Questions In Large Language Model Powered Conversational Agents, Yue Chen, Chen Huang, Yang Deng, Wenqiang Lei, Dingnan Jin, Jia Liu, Tat-Seng Chua Aug 2024

Style: Improving Domain Transferability Of Asking Clarification Questions In Large Language Model Powered Conversational Agents, Yue Chen, Chen Huang, Yang Deng, Wenqiang Lei, Dingnan Jin, Jia Liu, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Equipping a conversational search engine with strategies regarding when to ask clarification questions is becoming increasingly important across various domains. Attributing to the context understanding capability of LLMs and their access to domain-specific sources of knowledge, LLM-based clarification strategies feature rapid transfer to various domains in a posthoc manner. However, they still struggle to deliver promising performance on unseen domains, struggling to achieve effective domain transferability. We take the first step to investigate this issue and existing methods tend to produce one-size-fits-all strategies across diverse domains, limiting their search effectiveness. In response, we introduce a novel method, called STYLE, to …

Go to article

Chain-Of-Exemplar: Enhancing Distractor Generation For Multimodal Educational Question Generation, Haohao Luo, Yang Deng, Ying Shen, See-Kiong Ng, Tat-Seng Chua Aug 2024

Chain-Of-Exemplar: Enhancing Distractor Generation For Multimodal Educational Question Generation, Haohao Luo, Yang Deng, Ying Shen, See-Kiong Ng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Multiple-choice questions (MCQs) are important in enhancing concept learning and student engagement for educational purposes. Despite the multimodal nature of educational content, current methods focus mainly on text-based inputs and often neglect the integration of visual information. In this work, we study the problem of multimodal educational question generation, which aims at generating subject-specific educational questions with plausible yet incorrect distractors based on multimodal educational content. To tackle this problem, we introduce a novel framework, named Chain-of-Exemplar (CoE), which utilizes multimodal large language models (MLLMs) with Chain-of-Thought reasoning to improve the generation of challenging distractors. Furthermore, CoE leverages three-stage contextualized …

Go to article

On The Multi-Turn Instruction Following For Conversational Web Agents, Yang Deng, Xuan Zhang, Wenxuan Zhang, Yifei Yuan, See-Kiong Ng, Tat-Seng Chua Aug 2024

On The Multi-Turn Instruction Following For Conversational Web Agents, Yang Deng, Xuan Zhang, Wenxuan Zhang, Yifei Yuan, See-Kiong Ng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Web agents powered by Large Language Models (LLMs) have demonstrated remarkable abilities in planning and executing multi-step interactions within complex web-based environments, fulfilling a wide range of web navigation tasks. Despite these advancements, the potential for LLM-powered agents to effectively engage with sequential user instructions in real-world scenarios has not been fully explored. In this work, we introduce a new task of Conversational Web Navigation, which necessitates sophisticated interactions that span multiple turns with both the users and the environment, supported by a specially developed dataset named Multi-Turn Mind2Web (MT-Mind2Web). To tackle the limited context length of LLMs and the …

Go to article

Watme: Towards Lossless Watermarking Through Lexical Redundancy, Liang Chen, Yatao Bian, Yang Deng, Deng Cai, Shuaiyi Li, Peilin Zhao, Kam-Fai Wong Aug 2024

Watme: Towards Lossless Watermarking Through Lexical Redundancy, Liang Chen, Yatao Bian, Yang Deng, Deng Cai, Shuaiyi Li, Peilin Zhao, Kam-Fai Wong

Research Collection School Of Computing and Information Systems

Text watermarking has emerged as a pivotal technique for identifying machine-generated text. However, existing methods often rely on arbitrary vocabulary partitioning during decoding to embed watermarks, which compromises the availability of suitable tokens and significantly degrades the quality of responses. This study assesses the impact of watermarking on different capabilities of large language models (LLMs) from a cognitive science lens. Our finding highlights a significant disparity; knowledge recall and logical reasoning are more adversely affected than language generation. These results suggest a more profound effect of watermarking on LLMs than previously understood. To address these challenges, we introduce Watermarking with …

Go to article

Clamber: A Benchmark Of Identifying And Clarifying Ambiguous Information Needs In Large Language Models, Tong Zhang, Peixin Qin, Yang Deng, Chen Huang, Wenqiang Lei, Junhong Liu, Dingnan Jin, Hongru Liang, Tat-Seng Chua Aug 2024

Clamber: A Benchmark Of Identifying And Clarifying Ambiguous Information Needs In Large Language Models, Tong Zhang, Peixin Qin, Yang Deng, Chen Huang, Wenqiang Lei, Junhong Liu, Dingnan Jin, Hongru Liang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Large language models (LLMs) are increasingly used to meet user information needs, but their effectiveness in dealing with user queries that contain various types of ambiguity remains unknown, ultimately risking user trust and satisfaction. To this end, we introduce CLAMBER, a benchmark for evaluating LLMs using a well-organized taxonomy. Building upon the taxonomy, we construct 12K high-quality data to assess the strengths, weaknesses, and potential risks of various off-the-shelf LLMs.Our findings indicate the limited practical utility of current LLMs in identifying and clarifying ambiguous user queries, even enhanced by chain-of-thought (CoT) and few-shot prompting. These techniques may result in overconfidence …

Go to article

Self-Chats From Large Language Models Make Small Emotional Support Chatbot Better, Zhonghua Zheng, Lizi Liao, Yang Deng, Libo Qin, Liqiang Nie Aug 2024

Self-Chats From Large Language Models Make Small Emotional Support Chatbot Better, Zhonghua Zheng, Lizi Liao, Yang Deng, Libo Qin, Liqiang Nie

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have shown strong generalization abilities to excel in various tasks, including emotion support conversations. However, deploying such LLMs like GPT-3 (175B parameters) is resource-intensive and challenging at scale. In this study, we utilize LLMs as “Counseling Teacher” to enhance smaller models’ emotion support response abilities, significantly reducing the necessity of scaling up model size. To this end, we first introduce an iterative expansion framework, aiming to prompt the large teacher model to curate an expansive emotion support dialogue dataset. This curated dataset, termed ExTES, encompasses a broad spectrum of scenarios and is crafted with meticulous strategies …

Go to article

Reinforcement Tuning For Detecting Stances And Debunking Rumors Jointly With Large Language Models, Ruichao Yang, Wei Gao, Jing Ma, Hongzhan Ling, Bo Wang Aug 2024

Reinforcement Tuning For Detecting Stances And Debunking Rumors Jointly With Large Language Models, Ruichao Yang, Wei Gao, Jing Ma, Hongzhan Ling, Bo Wang

Research Collection School Of Computing and Information Systems

Learning multi-task models for jointly detecting stance and verifying rumors poses challenges due to the need for training data of stance at post level and rumor veracity at claim level, which are difficult to obtain. To address this issue, we leverage large language models (LLMs) as the foundation annotators for the joint stance detection (SD) and rumor verification (RV) tasks, dubbed as JSDRV. We introduce a novel reinforcement tuning framework to enhance the joint predictive capabilities of LLM-based SD and RV components. Specifically, we devise a policy for selecting LLM-annotated data at the two levels, employing a hybrid reward mechanism …

Go to article

Larp: Language Audio Relational Pre‑Training For Cold‑Start Playlist Continuation, Rebecca Salganik, Xiaohao Liu, Yunshan Ma, Jian Kang, Tat‑Seng Chua Aug 2024

Larp: Language Audio Relational Pre‑Training For Cold‑Start Playlist Continuation, Rebecca Salganik, Xiaohao Liu, Yunshan Ma, Jian Kang, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

As online music consumption increasingly shifts towards playlist-based listening, the task of playlist continuation, in which an algorithm suggests songs to extend a playlist in a personalized and musically cohesive manner, has become vital to the success of music streaming services. Currently, many existing playlist continuation approaches rely on collaborative filtering methods to perform their recommendations. However, such methods will struggle to recommend songs that lack interaction data, an issue known as the cold-start problem. Current approaches to this challenge design complex mechanisms for extracting relational signals from sparse collaborative signals and integrating them into content representations. However, these approaches …

Go to article

Large Language Model Powered Agents For Information Retrieval, An Zhang, Yang Deng, Yankai Lin, Xu Chen, Ji-Rong Wen, Tat-Seng Chua Jul 2024

Large Language Model Powered Agents For Information Retrieval, An Zhang, Yang Deng, Yankai Lin, Xu Chen, Ji-Rong Wen, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

The vital goal of information retrieval today extends beyond merely connecting users with relevant information they search for. It also aims to enrich the diversity, personalization, and interactivity of that connection, ensuring the information retrieval process is as seamless, beneficial, and supportive as possible in the global digital era. Current information retrieval systems often encounter challenges like a constrained understanding of queries, static and inflexible responses, limited personalization, and restricted interactivity. With the advent of large language models (LLMs), there's a transformative paradigm shift as we integrate LLM-powered agents into these systems. These agents bring forth crucial human capabilities like …

Go to article

Let’S Think Outside The Box: Exploring Leap-Of-Thought In Large Language Models With Multimodal Humor Generation, Shanshan Zhong, Zhongzhan Huang, Shanghua Gao, Wushao Wen, Liang Lin, Marinka Zitnik, Pan Zhou Jun 2024

Let’S Think Outside The Box: Exploring Leap-Of-Thought In Large Language Models With Multimodal Humor Generation, Shanshan Zhong, Zhongzhan Huang, Shanghua Gao, Wushao Wen, Liang Lin, Marinka Zitnik, Pan Zhou

Research Collection School Of Computing and Information Systems

Chain-of-Thought (CoT) [2, 3] guides large language models (LLMs) to reason step-by-step, and can motivate their logical reasoning ability. While effective for logical tasks, CoT is not conducive to creative problem-solving which often requires out-of-box thoughts and is crucial for innovation advancements. In this paper, we explore the Leap-of-Thought (LoT) abilities within LLMs — a nonsequential, creative paradigm involving strong associations and knowledge leaps. To this end, we study LLMs on the popular Oogiri game which needs participants to have good creativity and strong associative thinking for responding unexpectedly and humorously to the given image, text, or both, and thus …

Go to article

Compositional Policy Learning In Stochastic Control Systems With Formal Guarantees, Dorde Zikelic, Mathias Lechner, Abhinav Verma, Krishnendu Chatterjee, Thomas A. Henzinger May 2024

Compositional Policy Learning In Stochastic Control Systems With Formal Guarantees, Dorde Zikelic, Mathias Lechner, Abhinav Verma, Krishnendu Chatterjee, Thomas A. Henzinger

Research Collection School Of Computing and Information Systems

Reinforcement learning has shown promising results in learning neural network policies for complicated control tasks. However, the lack of formal guarantees about the behavior of such policies remains an impediment to their deployment. We propose a novel method for learning a composition of neural network policies in stochastic environments, along with a formal certificate which guarantees that a specification over the policy's behavior is satisfied with the desired probability. Unlike prior work on verifiable RL, our approach leverages the compositional nature of logical specifications provided in SPECTRL, to learn over graphs of probabilistic reach-avoid specifications. The formal guarantees are provided …

Go to article

Unveiling Code Pre-Trained Models: Investigating Syntax And Semantics Capacities, Wei Ma, Shangqing Liu, Mengjie Zhao, Xiaofei Xie, Wenhang Wang, Qiang Hu, Jie Zhang, Liu Yang May 2024

Unveiling Code Pre-Trained Models: Investigating Syntax And Semantics Capacities, Wei Ma, Shangqing Liu, Mengjie Zhao, Xiaofei Xie, Wenhang Wang, Qiang Hu, Jie Zhang, Liu Yang

Research Collection School Of Computing and Information Systems

Code models have made significant advancements in code intelligence by encoding knowledge about programming languages. While previous studies have explored the capabilities of these models in learning code syntax, there has been limited investigation on their ability to understand code semantics. Additionally, existing analyses assume the number of edges between nodes at the abstract syntax tree (AST) is related to syntax distance, and also often require transforming the high-dimensional space of deep learning models to a low-dimensional one, which may introduce inaccuracies. To study how code models represent code syntax and semantics, we conduct a comprehensive analysis of 7 code …

Go to article

Large Language Model Powered Agents In The Web, Yang Deng, An Zhang, Yankai Lin, Xu Chen, Ji-Rong Wen, Tat-Seng Chua May 2024

Large Language Model Powered Agents In The Web, Yang Deng, An Zhang, Yankai Lin, Xu Chen, Ji-Rong Wen, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Web applications serve as vital interfaces for users to access information, perform various tasks, and engage with content. Traditional web designs have predominantly focused on user interfaces and static experiences. With the advent of large language models (LLMs), there’s a paradigm shift as we integrate LLM-powered agents into these platforms. These agents bring forth crucial human capabilities like memory and planning to make them behave like humans in completing various tasks, effectively enhancing user engagement and offering tailored interactions in web applications. In this tutorial, we delve into the cutting-edge techniques of LLM-powered agents across various web applications, such as …

Go to article

Plug-And-Play Policy Planner For Large Language Model Powered Dialogue Agents, Yang Deng, Wenxuan Zhang, Wai Lam, See-Kiong Ng, Tat-Seng Chua May 2024

Plug-And-Play Policy Planner For Large Language Model Powered Dialogue Agents, Yang Deng, Wenxuan Zhang, Wai Lam, See-Kiong Ng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Proactive dialogues serve as a practical yet challenging dialogue problem in the era of large language models (LLMs), where the dialogue policy planning is the key to improving the proactivity of LLMs. Most existing studies enable the dialogue policy planning of LLMs using various prompting schemes or iteratively enhance this capability in handling the given case with verbal AI feedback. However, these approaches are either bounded by the policy planning capability of the frozen LLMs or hard to be transferred to new cases. In this work, we introduce a new dialogue policy planning paradigm to strategize LLMs for proactive dialogue …

Go to article

Learning To Generate Explainable Stock Predictions Using Self‑Reflective Large Language Models, Kelvin J.L. Koa, Yunshan Ma, Ritchie Ng, Tat‑Seng Chua May 2024

Learning To Generate Explainable Stock Predictions Using Self‑Reflective Large Language Models, Kelvin J.L. Koa, Yunshan Ma, Ritchie Ng, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

Explaining stock predictions is generally a difficult task for traditional non-generative deep learning models, where explanations are limited to visualizing the attention weights on important texts. Today, Large Language Models (LLMs) present a solution to this problem, given their known capabilities to generate human-readable explanations for their decision-making process. However, the task of stock prediction remains challenging for LLMs, as it requires the ability to weigh the varying impacts of chaotic social texts on stock prices. The problem gets progressively harder with the introduction of the explanation component, which requires LLMs to explain verbally why certain factors are more important …

Go to article

Enhancing Visual Grounding In Vision-Language Pre-Training With Position-Guided Text Prompts, Alex Jinpeng Wang, Pan Zhou, Mike Zheng Shou, Shuicheng Yan May 2024

Enhancing Visual Grounding In Vision-Language Pre-Training With Position-Guided Text Prompts, Alex Jinpeng Wang, Pan Zhou, Mike Zheng Shou, Shuicheng Yan

Research Collection School Of Computing and Information Systems

Vision-Language Pre-Training (VLP) has demonstrated remarkable potential in aligning image and text pairs, paving the way for a wide range of cross-modal learning tasks. Nevertheless, we have observed that VLP models often fall short in terms of visual grounding and localization capabilities, which are crucial for many downstream tasks, such as visual reasoning. In response, we introduce a novel Position-guided Text Prompt ( PTP ) paradigm to bolster the visual grounding abilities of cross-modal models trained with VLP. In the VLP phase, PTP divides an image into N x N blocks and employs a widely-used object detector to identify objects …

Go to article

Large Language Models For Qualitative Research In Software Engineering: Exploring Opportunities And Challenges, Muneera Bano, Rashina Hoda, Didar Zowghi, Christoph Treude May 2024

Large Language Models For Qualitative Research In Software Engineering: Exploring Opportunities And Challenges, Muneera Bano, Rashina Hoda, Didar Zowghi, Christoph Treude

Research Collection School Of Computing and Information Systems

The recent surge in the integration of Large Language Models (LLMs) like ChatGPT into qualitative research in software engineering, much like in other professional domains, demands a closer inspection. This vision paper seeks to explore the opportunities of using LLMs in qualitative research to address many of its legacy challenges as well as potential new concerns and pitfalls arising from the use of LLMs. We share our vision for the evolving role of the qualitative researcher in the age of LLMs and contemplate how they may utilize LLMs at various stages of their research experience.

Go to article

Large Language Model For Vulnerability Detection: Emerging Results And Future Directions, Xin Zhou, Ting Zhang, David Lo Apr 2024

Large Language Model For Vulnerability Detection: Emerging Results And Future Directions, Xin Zhou, Ting Zhang, David Lo

Research Collection School Of Computing and Information Systems

Previous learning-based vulnerability detection methods relied on either medium-sized pre-trained models or smaller neural networks from scratch. Recent advancements in Large Pre-Trained Language Models (LLMs) have showcased remarkable few-shot learning capabilities in various tasks. However, the effectiveness of LLMs in detecting software vulnerabilities is largely unexplored. This paper aims to bridge this gap by exploring how LLMs perform with various prompts, particularly focusing on two state-of-the-art LLMs: GPT-3.5 and GPT-4. Our experimental results showed that GPT-3.5 achieves competitive performance with the prior state-of-the-art vulnerability detection approach and GPT-4 consistently outperformed the state-of-the-art.

Go to article

Code Search Is All You Need? Improving Code Suggestions With Code Search, Junkai Chen, Xing Hu, Zhenhao Li, Cuiyun Gao, Xin Xia, David Lo Apr 2024

Code Search Is All You Need? Improving Code Suggestions With Code Search, Junkai Chen, Xing Hu, Zhenhao Li, Cuiyun Gao, Xin Xia, David Lo

Research Collection School Of Computing and Information Systems

Modern integrated development environments (IDEs) provide various automated code suggestion techniques (e.g., code completion and code generation) to help developers improve their efficiency. Such techniques may retrieve similar code snippets from the code base or leverage deep learning models to provide code suggestions. However, how to effectively enhance the code suggestions using code retrieval has not been systematically investigated. In this paper, we study and explore a retrieval-augmented framework for code suggestions. Specifically, our framework leverages different retrieval approaches and search strategies to search similar code snippets. Then the retrieved code is used to further enhance the performance of language …

Go to article

First Prev Next Last