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

Computer Sciences Commons™

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

Singapore Management University

Discipline
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 1591 - 1620 of 9003

Full-Text Articles in Computer Sciences

Supporting Software Engineers With Large Language Model-Based Automation, Ting Zhang Dec 2023

Supporting Software Engineers With Large Language Model-Based Automation, Ting Zhang

Dissertations and Theses Collection (Open Access)

In recent years, software engineering (SE) has witnessed significant growth, leading to the creation and sharing of an abundance of software artifacts such as source code, bug reports, and pull requests. Analyzing these artifacts is crucial for comprehending the sentiments of software developers and automating various SE tasks, ultimately leading to more human-centered automated SE and enhancing software development efficiency. However, the diverse and unstructured nature of software text poses a significant challenge to this analysis. In response, researchers have investigated a variety of approaches, including the utilization of natural language processing techniques. The advent of large language models (LLMs), …

Go to article

Towards Securing Smart Contracts Systematically, Duy Tai Nguyen Dec 2023

Towards Securing Smart Contracts Systematically, Duy Tai Nguyen

Dissertations and Theses Collection (Open Access)

Smart contracts are a groundbreaking technique that allows users to programmatically modify the state of the blockchain. They are essentially self-enforcing programs that are deployed and executed on top of the blockchain. In recent years, we have witnessed various smart contract incidents that led to substantial financial losses and even business closures. These incidents mainly arise from design flaws in Solidity, a dominant programming language for writing smart contracts, which complicates the process of detecting and repairing vulnerabilities. Furthermore, there is a growing interest in attacking smart contracts by the attackers. This thesis is dedicated to developing effective methods to …

Go to article

Distxplore: Distribution-Guided Testing For Evaluating And Enhancing Deep Learning Systems, Longtian Wang, Xiaofei Xie, Xiaoning Du, Meng Tian, Qing Guo, Zheng Yang, Chao Shen Dec 2023

Distxplore: Distribution-Guided Testing For Evaluating And Enhancing Deep Learning Systems, Longtian Wang, Xiaofei Xie, Xiaoning Du, Meng Tian, Qing Guo, Zheng Yang, Chao Shen

Research Collection School Of Computing and Information Systems

Deep learning (DL) models are trained on sampled data, where the distribution of training data differs from that of real-world data (i.e., the distribution shift), which reduces the model's robustness. Various testing techniques have been proposed, including distribution-unaware and distribution-aware methods. However, distribution-unaware testing lacks effectiveness by not explicitly considering the distribution of test cases and may generate redundant errors (within same distribution). Distribution-aware testing techniques primarily focus on generating test cases that follow the training distribution, missing out-of-distribution data that may also be valid and should be considered in the testing process. In this paper, we propose a novel …

Go to article

Software Architecture In Practice: Challenges And Opportunities, Zhiyuan Wan, Yun Zhang, Xin Xia, Yi Jiang, David Lo Dec 2023

Software Architecture In Practice: Challenges And Opportunities, Zhiyuan Wan, Yun Zhang, Xin Xia, Yi Jiang, David Lo

Research Collection School Of Computing and Information Systems

Software architecture has been an active research field for nearly four decades, in which previous studies make significant progress such as creating methods and techniques and building tools to support software architecture practice. Despite past efforts, we have little understanding of how practitioners perform software architecture related activities, and what challenges they face. Through interviews with 32 practitioners from 21 organizations across three continents, we identified challenges that practitioners face in software architecture practice during software development and maintenance. We reported on common software architecture activities at software requirements, design, construction and testing, and maintenance stages, as well as corresponding …

Go to article

Monocular Depth Estimation For Glass Walls With Context: A New Dataset And Method, Yuan Liang, Bailin Deng, Wenxi Liu, Jing Qin, Shengfeng He Dec 2023

Monocular Depth Estimation For Glass Walls With Context: A New Dataset And Method, Yuan Liang, Bailin Deng, Wenxi Liu, Jing Qin, Shengfeng He

Research Collection School Of Computing and Information Systems

Traditional monocular depth estimation assumes that all objects are reliably visible in the RGB color domain. However, this is not always the case as more and more buildings are decorated with transparent glass walls. This problem has not been explored due to the difficulties in annotating the depth levels of glass walls, as commercial depth sensors cannot provide correct feedbacks on transparent objects. Furthermore, estimating depths from transparent glass walls requires the aids of surrounding context, which has not been considered in prior works. To cope with this problem, we introduce the first Glass Walls Depth Dataset (GW-Depth dataset). We …

Go to article

On The Usage Of Continual Learning For Out-Of-Distribution Generalization In Pre-Trained Language Models Of Code, Martin Weyssow, Xin Zhou, Kisub Kim, David Lo, Houari A. Sahraoui Dec 2023

On The Usage Of Continual Learning For Out-Of-Distribution Generalization In Pre-Trained Language Models Of Code, Martin Weyssow, Xin Zhou, Kisub Kim, David Lo, Houari A. Sahraoui

Research Collection School Of Computing and Information Systems

Pre-trained language models (PLMs) have become a prevalent technique in deep learning for code, utilizing a two-stage pre-training and fine-tuning procedure to acquire general knowledge about code and specialize in a variety of downstream tasks. However, the dynamic nature of software codebases poses a challenge to the effectiveness and robustness of PLMs. In particular, world-realistic scenarios potentially lead to significant differences between the distribution of the pre-training and test data, i.e., distribution shift, resulting in a degradation of the PLM's performance on downstream tasks. In this paper, we stress the need for adapting PLMs of code to software data whose …

Go to article

Clusterprompt: Cluster Semantic Enhanced Prompt Learning For New Intent Discovery, Jinggui Liang, Lizi Liao Dec 2023

Clusterprompt: Cluster Semantic Enhanced Prompt Learning For New Intent Discovery, Jinggui Liang, Lizi Liao

Research Collection School Of Computing and Information Systems

The discovery of new intent categories from user utterances is a crucial task in expanding agent skills. The key lies in how to efficiently solicit semantic evidence from utterances and properly transfer knowledge from existing intents to new intents. However, previous methods laid too much emphasis on relations among utterances or clusters for transfer learning, while paying less attention to the usage of semantics. As a result, these methods suffer from in-domain over-fitting and often generate meaningless new intent clusters due to data distortion. In this paper, we present a novel approach called Cluster Semantic Enhanced Prompt Learning (CsePL) for …

Go to article

A Big Data Approach To Augmenting The Huff Model With Road Network And Mobility Data For Store Footfall Prediction, Ming Hui Tan, Kar Way Tan, Hoong Chuin Lau Dec 2023

A Big Data Approach To Augmenting The Huff Model With Road Network And Mobility Data For Store Footfall Prediction, Ming Hui Tan, Kar Way Tan, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Conventional methodologies for new retail store catchment area and footfall estimation rely on ground surveys which are costly and time-consuming. This study augments existing research in footfall estimation through the innovative integration of mobility data and road network to create population-weighted centroids and delineate residential neighbourhoods via a community detection algorithm. Our findings are then used to enhance Huff Model which is commonly used in site selection and footfall estimation. Our approach demonstrated the vast potential residing within big data where we harness the power of mobility data and road network information, offering a cost-effective and scalable alternative. It obviates …

Go to article

Vision Paper: Advancing Of Ai Explainability For The Use Of Chatgpt In Government Agencies: Proposal Of A 4-Step Framework, Hui Shan Lee, Shankararaman, Venky, Eng Lieh Ouh Dec 2023

Vision Paper: Advancing Of Ai Explainability For The Use Of Chatgpt In Government Agencies: Proposal Of A 4-Step Framework, Hui Shan Lee, Shankararaman, Venky, Eng Lieh Ouh

Research Collection School Of Computing and Information Systems

This paper explores ChatGPT’s potential in aiding government agencies, drawing from a case study based on a government agency in Singapore. While ChatGPT’s text generation abilities offer promise, it brings inherent challenges, including data opacity, potential misinformation, and occasional errors. These issues are especially critical in government decision-making.Public administration’s core values of transparency and accountability magnify these concerns. Ensuring AI alignment with these principles is imperative, given the potential repercussions on policy outcomes and citizen trust.AI explainability plays a central role in ChatGPT’s adoption within government agencies. To address these concerns, we propose strategies like prompt engineering, data governance, and …

Go to article

Sustainability Projects With A Community Partner: A Social Norm Nudging Effort, Benjamin Gan, Thomas Menkhoff, Eng Lieh Ouh Dec 2023

Sustainability Projects With A Community Partner: A Social Norm Nudging Effort, Benjamin Gan, Thomas Menkhoff, Eng Lieh Ouh

Research Collection School Of Computing and Information Systems

Singapore students from two inter-disciplinary courses worked with stakeholders of a local business association community partner on a series of sustainability topics to learn about climate change, its effects, and actions to mitigate them. They empathized with the association stakeholders, proposed a digital technology solution, tested their prototypes, and presented the final action plans. After the projects were completed, we found climate proficient (83%), motivated (83%), engaged (97%), and satisfied (70%) students; and two influencing predictors: interest/enjoyment and emotional engagement. The study results suggest that getting students interested and emotionally engaged in sustainability projects is an important first step towards …

Go to article

Scalelong: Towards More Stable Training Of Diffusion Model Via Scaling Network Long Skip Connection, Zhongzhan Huang, Pan Zhou, Shuicheng Yan, Liang Lin Dec 2023

Scalelong: Towards More Stable Training Of Diffusion Model Via Scaling Network Long Skip Connection, Zhongzhan Huang, Pan Zhou, Shuicheng Yan, Liang Lin

Research Collection School Of Computing and Information Systems

In diffusion models, UNet is the most popular network backbone, since its long skip connects (LSCs) to connect distant network blocks can aggregate long-distant information and alleviate vanishing gradient. Unfortunately, UNet often suffers from unstable training in diffusion models which can be alleviated by scaling its LSC coefficients smaller. However, theoretical understandings of the instability of UNet in diffusion models and also the performance improvement of LSC scaling remain absent yet. To solve this issue, we theoretically show that the coefficients of LSCs in UNet have big effects on the stableness of the forward and backward propagation and robustness of …

Go to article

Estimating Propensity For Causality-Based Recommendation Without Exposure Data, Zhongzhou Liu, Yuan Fang, Min Wu Dec 2023

Estimating Propensity For Causality-Based Recommendation Without Exposure Data, Zhongzhou Liu, Yuan Fang, Min Wu

Research Collection School Of Computing and Information Systems

Causality-based recommendation systems focus on the causal effects of user-item interactions resulting from item exposure (i.e., which items are recommended or exposed to the user), as opposed to conventional correlation-based recommendation. They are gaining popularity due to their multi-sided benefits to users, sellers and platforms alike. However, existing causality-based recommendation methods require additional input in the form of exposure data and/or propensity scores (i.e., the probability of exposure) for training. Such data, crucial for modeling causality in recommendation, are often not available in real-world situations due to technical or privacy constraints. In this paper, we bridge the gap by proposing …

Go to article

Llm-Adapters: An Adapter Family For Parameter-Efficient Fine-Tuning Of Large Language Models, Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Lidong Bing, Xing Xu, Soujanya Poria, Roy Ka-Wei Lee Dec 2023

Llm-Adapters: An Adapter Family For Parameter-Efficient Fine-Tuning Of Large Language Models, Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Lidong Bing, Xing Xu, Soujanya Poria, Roy Ka-Wei Lee

Research Collection School Of Computing and Information Systems

The success of large language models (LLMs), like GPT-4 and ChatGPT, has led to the development of numerous cost-effective and accessible alternatives that are created by finetuning open-access LLMs with task-specific data (e.g., ChatDoctor) or instruction data (e.g., Alpaca). Among the various fine-tuning methods, adapter-based parameter-efficient fine-tuning (PEFT) is undoubtedly one of the most attractive topics, as it only requires fine-tuning a few external parameters instead of the entire LLMs while achieving comparable or even better performance. To enable further research on PEFT methods of LLMs, this paper presents LLMAdapters, an easy-to-use framework that integrates various adapters into LLMs and …

Go to article

Video Sentiment Analysis For Child Safety, Yee Sen Tan, Nicole Anne Huiying Teo, Ezekiel En Zhe Ghe, Jolie Zhi Yi Fong, Zhaoxia Wang Dec 2023

Video Sentiment Analysis For Child Safety, Yee Sen Tan, Nicole Anne Huiying Teo, Ezekiel En Zhe Ghe, Jolie Zhi Yi Fong, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

The proliferation of online video content underscores the critical need for effective sentiment analysis, particularly in safeguarding children from potentially harmful material. This research addresses this concern by presenting a multimodal analysis method for assessing video sentiment, categorizing it as either positive (child-friendly) or negative (potentially harmful). This method leverages three key components: text analysis, facial expression analysis, and audio analysis, including music mood analysis, resulting in a comprehensive sentiment assessment. Our evaluation results validate the effectiveness of this approach, making significant contributions to the field of video sentiment analysis and bolstering child safety measures. This research serves as a …

Go to article

Examining The Inter-Consistency Of Large Language Models: An In-Depth Analysis Via Debate, Kai Xiong, Xiao Ding, Yixin Cao, Ting Liu, Bing Qin Dec 2023

Examining The Inter-Consistency Of Large Language Models: An In-Depth Analysis Via Debate, Kai Xiong, Xiao Ding, Yixin Cao, Ting Liu, Bing Qin

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have shown impressive capabilities in various applications, but they still face various inconsistency issues. Existing works primarily focus on the inconsistency issues within a single LLM, while we complementarily explore the inter-consistency among multiple LLMs for collaboration. To examine whether LLMs can collaborate effectively to achieve a consensus for a shared goal, we focus on commonsense reasoning, and introduce a formal debate framework (FORD) to conduct a three-stage debate among LLMs with real-world scenarios alignment: fair debate, mismatched debate, and roundtable debate. Through extensive experiments on various datasets, LLMs can effectively collaborate to reach a consensus …

Go to article

Metabox: A Benchmark Platform For Meta-Black-Box Optimization With Reinforcement Learning, Zeyuan Ma, Hongshu Guo, Jiacheng Chen, Zhenrui Li, Guojun Peng, Yue-Jiao Gong, Yining Ma, Zhiguang Cao Dec 2023

Metabox: A Benchmark Platform For Meta-Black-Box Optimization With Reinforcement Learning, Zeyuan Ma, Hongshu Guo, Jiacheng Chen, Zhenrui Li, Guojun Peng, Yue-Jiao Gong, Yining Ma, Zhiguang Cao

Research Collection School Of Computing and Information Systems

Recently, Meta-Black-Box Optimization with Reinforcement Learning (MetaBBO-RL) has showcased the power of leveraging RL at the meta-level to mitigate manual fine-tuning of lower-level black-box optimizers. However, this field is hindered by the lack of a unified benchmark. To fill this gap, we introduce MetaBox, the first benchmark platform expressly tailored for developing and evaluating MetaBBO-RL methods. MetaBox offers a flexible algorithmic template that allows users to effortlessly implement their unique designs within the platform. Moreover, it provides a broad spectrum of over 300 problem instances, collected from synthetic to realistic scenarios, and an extensive library of 19 baseline methods, including …

Go to article

Duties For Datasets, Jerrold Tsin Howe Soh Dec 2023

Duties For Datasets, Jerrold Tsin Howe Soh

Research Collection Yong Pung How School Of Law

Machine learning (ML) systems are increasingly being deployed in contexts, such as law, medicine and finance, where system errors present serious and foreseeable risks. As ML system behaviour is largely determined by their training inputs, should dataset providers owe duties of care to victims? Using the ImageNet dataset and the Generative Pre-trained Transformer (GPT) models as case studies, this chapter argues that the conventional approach of centralising duties on system providers alone yields insufficient safeguards. Dataset-specific duties should also be considered to incentivise precaution in the preparation of crucial ML input. The chapter analyses how dataset duties may be encompassed …

Go to article

Attack Prompt Generation For Red Teaming And Defending Large Language Models, Boyi Deng, Wenjie Wang, Fuli Feng, Yang Deng, Qifan Wang, Xiangnan He Dec 2023

Attack Prompt Generation For Red Teaming And Defending Large Language Models, Boyi Deng, Wenjie Wang, Fuli Feng, Yang Deng, Qifan Wang, Xiangnan He

Research Collection School Of Computing and Information Systems

Large language models (LLMs) are susceptible to red teaming attacks, which can induce LLMs to generate harmful content. Previous research constructs attack prompts via manual or automatic methods, which have their own limitations on construction cost and quality. To address these issues, we propose an integrated approach that combines manual and automatic methods to economically generate high-quality attack prompts. Specifically, considering the impressive capabilities of newly emerged LLMs, we propose an attack framework to instruct LLMs to mimic human-generated prompts through in-context learning. Furthermore, we propose a defense framework that fine-tunes victim LLMs through iterative interactions with the attack framework …

Go to article

Unifying Text, Tables, And Images For Multimodal Question Answering, Haohao Luo, Ying Shen, Yang Deng Dec 2023

Unifying Text, Tables, And Images For Multimodal Question Answering, Haohao Luo, Ying Shen, Yang Deng

Research Collection School Of Computing and Information Systems

Multimodal question answering (MMQA), which aims to derive the answer from multiple knowledge modalities (e.g., text, tables, and images), has received increasing attention due to its board applications. Current approaches to MMQA often rely on single-modal or bi-modal QA models, which limits their ability to effectively integrate information across all modalities and leverage the power of pre-trained language models. To address these limitations, we propose a novel framework called UniMMQA, which unifies three different input modalities into a text-to-text format by employing position-enhanced table linearization and diversified image captioning techniques. Additionally, we enhance cross-modal reasoning by incorporating a multimodal rationale …

Go to article

Deeparc: Modularizing Neural Networks For The Model Maintenance, Xiaoning Ren, Yun Lin, Yinxing Xue, Ruofan Liu, Jun Sun, Zhiyong Feng, Jinsong Dong Dec 2023

Deeparc: Modularizing Neural Networks For The Model Maintenance, Xiaoning Ren, Yun Lin, Yinxing Xue, Ruofan Liu, Jun Sun, Zhiyong Feng, Jinsong Dong

Research Collection School Of Computing and Information Systems

Neural networks are an emerging data-driven programming paradigm widely used in many areas. Unlike traditional software systems consisting of decomposable modules, a neural network is usually delivered as a monolithic package, raising challenges for some maintenance tasks such as model restructure and re-adaption. In this work, we propose DeepArc, a novel modularization method for neural networks, to reduce the cost of model maintenance tasks. Specifically, DeepArc decomposes a neural network into several consecutive modules, each of which encapsulates consecutive layers with similar semantics. The network modularization facilitates practical tasks such as refactoring the model to preserve existing features (e.g., model …

Go to article

Exgen: Ready-To-Use Exercise Generation In Introductory Programming Courses, Nguyen Binh Duong Ta, Hua Gia Phuc Nguyen, Gottipati Swapna Dec 2023

Exgen: Ready-To-Use Exercise Generation In Introductory Programming Courses, Nguyen Binh Duong Ta, Hua Gia Phuc Nguyen, Gottipati Swapna

Research Collection School Of Computing and Information Systems

In introductory programming courses, students as novice programmers would benefit from doing frequent practices set at a difficulty level and concept suitable for their skills and knowledge. However, setting many good programming exercises for individual learners is very time-consuming for instructors. In this work, we propose an automated exercise generation system, named ExGen, which leverages recent advances in pre-trained large language models (LLMs) to automatically create customized and ready-to-use programming exercises for individual students ondemand. The system integrates seamlessly with Visual Studio Code, a popular development environment for computing students and software engineers. ExGen effectively does the following: 1) maintaining …

Go to article

Offline Rl With Discrete Proxy Representations For Generalizability In Pomdps, Pengjie Gu, Xinyu Cai, Dong Xing, Xinrun Wang, Mengchen Zhao, Bo An Dec 2023

Offline Rl With Discrete Proxy Representations For Generalizability In Pomdps, Pengjie Gu, Xinyu Cai, Dong Xing, Xinrun Wang, Mengchen Zhao, Bo An

Research Collection School Of Computing and Information Systems

Offline Reinforcement Learning (RL) has demonstrated promising results in various applications by learning policies from previously collected datasets, reducing the need for online exploration and interactions. However, real-world scenarios usually involve partial observability, which brings crucial challenges of the deployment of offline RL methods: i) the policy trained on data with full observability is not robust against the masked observations during execution, and ii) the information of which parts of observations are masked is usually unknown during training. In order to address these challenges, we present Offline RL with DiscrEte pRoxy representations (ORDER), a probabilistic framework which leverages novel state …

Go to article

Large Language Models As Source Planner For Personalized Knowledge-Grounded Dialogues, Hongru Wang, Minda Hu, Yang Deng, Rui Wang, Fei Mi, Weichao Wang, Yasheng Wang, Wai-Chung Kwan, Irwin King, Kam-Fai Wong Dec 2023

Large Language Models As Source Planner For Personalized Knowledge-Grounded Dialogues, Hongru Wang, Minda Hu, Yang Deng, Rui Wang, Fei Mi, Weichao Wang, Yasheng Wang, Wai-Chung Kwan, Irwin King, Kam-Fai Wong

Research Collection School Of Computing and Information Systems

Open-domain dialogue system usually requires different sources of knowledge to generate more informative and evidential responses. However, existing knowledge-grounded dialogue systems either focus on a single knowledge source or overlook the dependency between multiple sources of knowledge, which may result in generating inconsistent or even paradoxical responses. To incorporate multiple knowledge sources and dependencies between them, we propose SAFARI, a novel framework that leverages the exceptional capabilities of large language models (LLMs) in planning, understanding, and incorporating under both supervised and unsupervised settings. Specifically, SAFARI decouples the knowledge grounding into multiple sources and response generation, which allows easy extension to …

Go to article

Controlling Type Confounding In Ad Hoc Teamwork With Instance-Wise Teammate Feedback Rectification, Dong Xing, Pengjie Gu, Qian Zheng, Xinrun Wang, Shanqi Liu, Longtao Zheng, Bo An, Gang Pan Dec 2023

Controlling Type Confounding In Ad Hoc Teamwork With Instance-Wise Teammate Feedback Rectification, Dong Xing, Pengjie Gu, Qian Zheng, Xinrun Wang, Shanqi Liu, Longtao Zheng, Bo An, Gang Pan

Research Collection School Of Computing and Information Systems

Ad hoc teamwork requires an agent to cooperate with unknown teammates without prior coordination. Many works propose to abstract teammate instances into high-level representation of types and then pre-train the best response for each type. However, most of them do not consider the distribution of teammate instances within a type. This could expose the agent to the hidden risk of type confounding. In the worst case, the best response for an abstract teammate type could be the worst response for all specific instances of that type. This work addresses the issue from the lens of causal inference. We first theoretically …

Go to article

Software Composition Analysis For Vulnerability Detection: An Empirical Study On Java Projects, Lida Zhao, Sen Chen, Zhengzi Xu, Lyuye Zhang, Jiahui Wu, Jun Sun, Yang Liu Dec 2023

Software Composition Analysis For Vulnerability Detection: An Empirical Study On Java Projects, Lida Zhao, Sen Chen, Zhengzi Xu, Lyuye Zhang, Jiahui Wu, Jun Sun, Yang Liu

Research Collection School Of Computing and Information Systems

Software composition analysis (SCA) tools are proposed to detect potential vulnerabilities introduced by open-source software (OSS) imported as third-party libraries (TPL). With the increasing complexity of software functionality, SCA tools may encounter various scenarios during the dependency resolution process, such as diverse formats of artifacts, diverse dependency imports, and diverse dependency specifications. However, there still lacks a comprehensive evaluation of SCA tools for Java that takes into account the above scenarios. This could lead to a confined interpretation of comparisons, improper use of tools, and hinder further improvements of the tools. To fill this gap, we proposed an Evaluation Model …

Go to article

Reinforced Target-Driven Conversational Promotion, Huy Quang Dao, Lizi Liao, Dung D. Le, Yuxiang Nie Dec 2023

Reinforced Target-Driven Conversational Promotion, Huy Quang Dao, Lizi Liao, Dung D. Le, Yuxiang Nie

Research Collection School Of Computing and Information Systems

The ability to proactively engage with users towards pitching products is highly desired for conversational assistants. However, existing conversational recommendation methods overemphasize on acquiring user preferences while ignore the strategic planning for nudging users towards accepting a designated item. Hence, these methods fail to promote specified items with engaging responses. In this work, we propose a Reinforced Target-driven Conversational Promotion (RTCP) framework for conversational promotion. RTCP integrates short-term and long-term planning via a balanced gating mechanism. Inside which, the dialogue actions are predicted via a knowledge-integrated multi-head attention and guided via reinforcement learning rewards. RTCP then employs action-guided prefix tuning …

Go to article

Rome: Evaluating Pre-Trained Vision-Language Models On Reasoning Beyond Visual Common Sense, Kankan Zhou, Eason Lai, Au Wei Bin Yeong, Kyriakos Mouratidis, Jing Jiang Dec 2023

Rome: Evaluating Pre-Trained Vision-Language Models On Reasoning Beyond Visual Common Sense, Kankan Zhou, Eason Lai, Au Wei Bin Yeong, Kyriakos Mouratidis, Jing Jiang

Research Collection School Of Computing and Information Systems

Humans possess a strong capability for reasoning beyond common sense. For example, given an unconventional image of a goldfish laying on the table next to an empty fishbowl, a human would effortlessly determine that the fish is not inside the fishbowl. The case, however, may be different for a vision-language model, whose reasoning could gravitate towards the common scenario that the fish is inside the bowl, despite the visual input. In this paper, we introduce a novel probing dataset named ROME (reasoning beyond commonsense knowledge) to evaluate whether the state-of-the-art pre-trained vision-language models have the reasoning capability to correctly interpret …

Go to article

Large Language Model Is Not A Good Few-Shot Information Extractor, But A Good Reranker For Hard Samples!, Yubo Ma, Yixin Cao, Yongchin Hong, Aixin Sun Dec 2023

Large Language Model Is Not A Good Few-Shot Information Extractor, But A Good Reranker For Hard Samples!, Yubo Ma, Yixin Cao, Yongchin Hong, Aixin Sun

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have made remarkable strides in various tasks. However, whether they are competitive few-shot solvers for information extraction (IE) tasks and surpass fine-tuned small Pre-trained Language Models (SLMs) remains an open problem. This paper aims to provide a thorough answer to this problem, and moreover, to explore an approach towards effective and economical IE systems that combine the strengths of LLMs and SLMs. Through extensive experiments on nine datasets across four IE tasks, we show that LLMs are not effective few-shot information extractors in general, given their unsatisfactory performance in most settings and the high latency and …

Go to article

Benchmarking Foundation Models With Language-Model-As-An-Examiner, Yushi Bai, Jiahao Ying, Yixin Cao, Xin Lv, Yuze He, Xiaozhi Wang, Jifan Yu, Kaisheng Zeng, Yijia Xiao, Haozhe Lyu, Jiayin Zhang, Juanzi Li, Lei Hou Dec 2023

Benchmarking Foundation Models With Language-Model-As-An-Examiner, Yushi Bai, Jiahao Ying, Yixin Cao, Xin Lv, Yuze He, Xiaozhi Wang, Jifan Yu, Kaisheng Zeng, Yijia Xiao, Haozhe Lyu, Jiayin Zhang, Juanzi Li, Lei Hou

Research Collection School Of Computing and Information Systems

Numerous benchmarks have been established to assess the performance of foundation models on open-ended question answering, which serves as a comprehensive test of a model’s ability to understand and generate language in a manner similar to humans. Most of these works focus on proposing new datasets, however, we see two main issues within previous benchmarking pipelines, namely testing leakage and evaluation automation. In this paper, we propose a novel benchmarking framework, Language-Model-as-an-Examiner, where the LM serves as a knowledgeable examiner that formulates questions based on its knowledge and evaluates responses in a reference-free manner. Our framework allows for effortless extensibility …

Go to article

Molca: Molecular Graph-Language Modeling With Cross-Modal Projector And Uni-Modal Adapter, Zhiyuan Liu, Sihang Li, Yanchen Luo, Hao Fei, Yixin Cao, Kenji Kawaguchi, Xiang Wang, Tat-Seng Chua Dec 2023

Molca: Molecular Graph-Language Modeling With Cross-Modal Projector And Uni-Modal Adapter, Zhiyuan Liu, Sihang Li, Yanchen Luo, Hao Fei, Yixin Cao, Kenji Kawaguchi, Xiang Wang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Language Models (LMs) have demonstrated impressive molecule understanding ability on various 1D text-related tasks. However, they inherently lack 2D graph perception — a critical ability of human professionals in comprehending molecules’ topological structures. To bridge this gap, we propose MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter. MolCA enables an LM (i.e., Galactica) to understand both text- and graph-based molecular contents via the cross-modal projector. Specifically, the cross-modal projector is implemented as a QFormer to connect a graph encoder’s representation space and an LM’s text space. Further, MolCA employs a uni-modal adapter (i.e., LoRA) for the LM’s efficient …

Go to article

First Prev Next Last