no code implementations • 17 Feb 2025 • Cheng Qian, Emre Can Acikgoz, Hongru Wang, Xiusi Chen, Avirup Sil, Dilek Hakkani-Tür, Gokhan Tur, Heng Ji
To support this paradigm, we introduce SMART-ER, a dataset spanning three domains, where reasoning alternates between parametric knowledge and tool-dependent steps, with each step enriched by rationales explaining when tools are necessary.
no code implementations • 21 Dec 2024 • Minda Hu, Qiyuan Zhang, YuFei Wang, Bowei He, Hongru Wang, Jingyan Zhou, Liangyou Li, Yasheng Wang, Chen Ma, Irwin King
However, existing IFT datasets often contain knowledge that is inconsistent with LLMs' internal knowledge learned from the pre-training phase, which can greatly affect the efficacy of IFT.
1 code implementation • 16 Dec 2024 • Boyang Xue, Fei Mi, Qi Zhu, Hongru Wang, Rui Wang, Sheng Wang, Erxin Yu, Xuming Hu, Kam-Fai Wong
Despite demonstrating impressive capabilities, Large Language Models (LLMs) still often struggle to accurately express the factual knowledge they possess, especially in cases where the LLMs' knowledge boundaries are ambiguous.
no code implementations • 15 Nov 2024 • Yutao Hou, Yajing Luo, Zhiwen Ruan, Hongru Wang, Weifeng Ge, Yun Chen, Guanhua Chen
In this paper, we introduce Compound Question Synthesis (CQ-Syn) to create the Compound-QA benchmark, focusing on compound questions with multiple sub-questions.
1 code implementation • 21 Oct 2024 • Yu Zhao, Alessio Devoto, Giwon Hong, Xiaotang Du, Aryo Pradipta Gema, Hongru Wang, Xuanli He, Kam-Fai Wong, Pasquale Minervini
In this work, we propose \textsc{SpARE}, a \emph{training-free} representation engineering method that uses pre-trained sparse auto-encoders (SAEs) to control the knowledge selection behaviour of LLMs.
1 code implementation • 21 Oct 2024 • Yu Zhao, Xiaotang Du, Giwon Hong, Aryo Pradipta Gema, Alessio Devoto, Hongru Wang, Xuanli He, Kam-Fai Wong, Pasquale Minervini
Through probing tasks, we find that LLMs can internally register the signal of knowledge conflict in the residual stream, which can be accurately detected by probing the intermediate model activations.
1 code implementation • 16 Oct 2024 • Boyang Xue, Hongru Wang, Rui Wang, Sheng Wang, Zezhong Wang, Yiming Du, Bin Liang, Kam-Fai Wong
This paper addresses this gap by introducing a comprehensive investigation of Multilingual Confidence estimation (MlingConf) on LLMs, focusing on both language-agnostic (LA) and language-specific (LS) tasks to explore the performance and language dominance effects of multilingual confidence estimations on different tasks.
1 code implementation • 10 Oct 2024 • Hongru Wang, Rui Wang, Boyang Xue, Heming Xia, Jingtao Cao, Zeming Liu, Jeff Z. Pan, Kam-Fai Wong
In this paper, we introduce \texttt{AppBench}, the first benchmark to evaluate LLMs' ability to plan and execute multiple APIs from various sources in order to complete the user's task.
1 code implementation • 8 Oct 2024 • WenYu Huang, Guancheng Zhou, Hongru Wang, Pavlos Vougiouklis, Mirella Lapata, Jeff Z. Pan
In this paper, we model the subgraph retrieval task as a conditional generation task handled by small language models.
1 code implementation • 23 Sep 2024 • Jingtao Cao, Zheng Zhang, Hongru Wang, Kam-Fai Wong
Progress in Text-to-Image (T2I) models has significantly improved the generation of images from textual descriptions.
1 code implementation • 2 Jul 2024 • Yan Yang, Zeguan Xiao, Xin Lu, Hongru Wang, Hailiang Huang, Guanhua Chen, Yun Chen
The widespread applications of large language models (LLMs) have brought about concerns regarding their potential misuse.
no code implementations • 17 Jun 2024 • Minda Hu, Licheng Zong, Hongru Wang, Jingyan Zhou, Jingjing Li, Yichen Gao, Kam-Fai Wong, Yu Li, Irwin King
By combining the reasoning capabilities of LLMs with the effectiveness of tree search, SeRTS boosts the zero-shot performance of retrieving high-quality and informative results for RAG.
no code implementations • 14 Jun 2024 • Jingtao Cao, Zheng Zhang, Hongru Wang, Bin Liang, Hao Wang, Kam-Fai Wong
Utilizing the BLIP model for image captioning, PP-OCR and TrOCR for text recognition across multiple languages, and the Qwen LLM for nuanced language understanding, our system is capable of identifying harmful content in memes created in English, Chinese, Malay, and Tamil.
2 code implementations • 27 May 2024 • Jianqiao Lu, Zhiyang Dou, Hongru Wang, Zeyu Cao, Jianbo Dai, Yingjia Wan, Zhijiang Guo
\textsc{AutoPSV} begins by training a verification model on the correctness of final answers, enabling it to generate automatic process annotations.
no code implementations • 17 May 2024 • Xiaoming Shi, Zeming Liu, Li Du, Yuxuan Wang, Hongru Wang, Yuhang Guo, Tong Ruan, Jie Xu, Shaoting Zhang
As a result, an overview of the categories, methods, and evaluation of medical dialogue systems remain limited and underspecified, hindering the further improvement of this area.
1 code implementation • 13 Mar 2024 • Rongwu Xu, Zehan Qi, Zhijiang Guo, Cunxiang Wang, Hongru Wang, Yue Zhang, Wei Xu
This survey provides an in-depth analysis of knowledge conflicts for large language models (LLMs), highlighting the complex challenges they encounter when blending contextual and parametric knowledge.
no code implementations • 5 Mar 2024 • Rui Wang, Fei Mi, Yi Chen, Boyang Xue, Hongru Wang, Qi Zhu, Kam-Fai Wong, Ruifeng Xu
2) Role Prompting assigns a central prompt to the general domain and a unique role prompt to each specific domain to minimize inter-domain confusion during training.
no code implementations • 26 Feb 2024 • Hongru Wang, Boyang Xue, Baohang Zhou, Rui Wang, Fei Mi, Weichao Wang, Yasheng Wang, Kam-Fai Wong
Conversational retrieval refers to an information retrieval system that operates in an iterative and interactive manner, requiring the retrieval of various external resources, such as persona, knowledge, and even response, to effectively engage with the user and successfully complete the dialogue.
no code implementations • 26 Feb 2024 • Yiming Du, Hongru Wang, Zhengyi Zhao, Bin Liang, Baojun Wang, Wanjun Zhong, Zezhong Wang, Kam-Fai Wong
This dataset is collected to investigate the use of personalized memories, focusing on social interactions and events in the QA task.
no code implementations • 21 Feb 2024 • Hongru Wang, Boyang Xue, Baohang Zhou, Tianhua Zhang, Cunxiang Wang, Huimin Wang, Guanhua Chen, Kam-Fai Wong
Previous research has typically concentrated on leveraging the internal knowledge of Large Language Models (LLMs) to answer known questions (i. e., \textit{internal reasoning such as generate-then-read}).
1 code implementation • 21 Feb 2024 • Boyang Xue, Hongru Wang, Rui Wang, Sheng Wang, Zezhong Wang, Yiming Du, Bin Liang, Kam-Fai Wong
This paper addresses this gap by introducing a comprehensive investigation of Multilingual Confidence estimation (MlingConf) on LLMs, focusing on both language-agnostic (LA) and language-specific (LS) tasks to explore the performance and language dominance effects of multilingual confidence estimations on different tasks.
no code implementations • 24 Jan 2024 • Hongru Wang, WenYu Huang, Yang Deng, Rui Wang, Zezhong Wang, YuFei Wang, Fei Mi, Jeff Z. Pan, Kam-Fai Wong
To better plan and incorporate the use of multiple sources in generating personalized response, we firstly decompose it into three sub-tasks: Knowledge Source Selection, Knowledge Retrieval, and Response Generation.
no code implementations • 28 Nov 2023 • Hongru Wang, Lingzhi Wang, Yiming Du, Liang Chen, Jingyan Zhou, YuFei Wang, Kam-Fai Wong
This survey delves into the historical trajectory of dialogue systems, elucidating their intricate relationship with advancements in language models by categorizing this evolution into four distinct stages, each marked by pivotal LM breakthroughs: 1) Early_Stage: characterized by statistical LMs, resulting in rule-based or machine-learning-driven dialogue_systems; 2) Independent development of TOD and ODD based on neural_language_models (NLM; e. g., LSTM and GRU), since NLMs lack intrinsic knowledge in their parameters; 3) fusion between different types of dialogue systems with the advert of pre-trained_language_models (PLMs), starting from the fusion between four_sub-tasks_within_TOD, and then TOD_with_ODD; and 4) current LLM-based_dialogue_system, wherein LLMs can be used to conduct TOD and ODD seamlessly.
no code implementations • 24 Oct 2023 • Zezhong Wang, Fangkai Yang, Lu Wang, Pu Zhao, Hongru Wang, Liang Chen, QIngwei Lin, Kam-Fai Wong
Currently, there are two main approaches to address jailbreak attacks: safety training and safeguards.
no code implementations • 13 Oct 2023 • Hongru Wang, Minda Hu, Yang Deng, Rui Wang, Fei Mi, Weichao Wang, Yasheng Wang, Wai-Chung Kwan, Irwin King, Kam-Fai Wong
Open-domain dialogue system usually requires different sources of knowledge to generate more informative and evidential responses.
1 code implementation • 12 Oct 2023 • Boyang Xue, Weichao Wang, Hongru Wang, Fei Mi, Rui Wang, Yasheng Wang, Lifeng Shang, Xin Jiang, Qun Liu, Kam-Fai Wong
Inspired by previous work which identified that feed-forward networks (FFNs) within Transformers are responsible for factual knowledge expressions, we investigate two methods to efficiently improve the factual expression capability {of FFNs} by knowledge enhancement and alignment respectively.
no code implementations • 28 Sep 2023 • Hongru Wang, Huimin Wang, Lingzhi Wang, Minda Hu, Rui Wang, Boyang Xue, Hongyuan Lu, Fei Mi, Kam-Fai Wong
Large language models (LLMs) have demonstrated exceptional performance in planning the use of various functional tools, such as calculators and retrievers, particularly in question-answering tasks.
1 code implementation • 1 Sep 2023 • Wai-Chung Kwan, Huimin Wang, Hongru Wang, Zezhong Wang, Xian Wu, Yefeng Zheng, Kam-Fai Wong
In addition, JoTR employs reinforcement learning with a reward-shaping mechanism to efficiently finetune the word-level dialogue policy, which allows the model to learn from its interactions, improving its performance over time.
1 code implementation • 23 May 2023 • Rui Wang, Hongru Wang, Fei Mi, Yi Chen, Boyang Xue, Kam-Fai Wong, Ruifeng Xu
Numerous works are proposed to align large language models (LLMs) with human intents to better fulfill instructions, ensuring they are trustful and helpful.
1 code implementation • 23 May 2023 • Yang Deng, Lizi Liao, Liang Chen, Hongru Wang, Wenqiang Lei, Tat-Seng Chua
Conversational systems based on Large Language Models (LLMs), such as ChatGPT, show exceptional proficiency in context understanding and response generation.
1 code implementation • 22 May 2023 • Liang Chen, Hongru Wang, Yang Deng, Wai-Chung Kwan, Zezhong Wang, Kam-Fai Wong
Generating persona consistent dialogue response is important for developing an intelligent conversational agent.
2 code implementations • 19 May 2023 • Hongru Wang, Rui Wang, Fei Mi, Yang Deng, Zezhong Wang, Bin Liang, Ruifeng Xu, Kam-Fai Wong
Large Language Models (LLMs), such as \texttt{ChatGPT}, greatly empower dialogue systems with strong language understanding and generation capabilities.
1 code implementation • 11 Oct 2022 • Zhiming Mao, Jian Li, Hongru Wang, Xingshan Zeng, Kam-Fai Wong
Second, existing graph-based NR methods are promising but lack effective news-user feature interaction, rendering the graph-based recommendation suboptimal.
no code implementations • 28 Feb 2022 • Wai-Chung Kwan, Hongru Wang, Huimin Wang, Kam-Fai Wong
In this paper, we survey recent advances and challenges in dialogue policy from the prescriptive of RL.
no code implementations • 2 Nov 2021 • Hongru Wang, Huimin Wang, Zezhong Wang, Kam-Fai Wong
Reinforcement Learning (RL) has been witnessed its potential for training a dialogue policy agent towards maximizing the accumulated rewards given from users.
no code implementations • 13 Oct 2021 • Hongru Wang, Zhijing Jin, Jiarun Cao, Gabriel Pui Cheong Fung, Kam-Fai Wong
However, previous works rarely investigate the effects of a different number of classes (i. e., $N$-way) and number of labeled data per class (i. e., $K$-shot) during training vs. testing.
no code implementations • 11 Sep 2021 • Hongru Wang, Mingyu Cui, Zimo Zhou, Gabriel Pui Cheong Fung, Kam-Fai Wong
A multi-turn dialogue always follows a specific topic thread, and topic shift at the discourse level occurs naturally as the conversation progresses, necessitating the model's ability to capture different topics and generate topic-aware responses.
no code implementations • 11 Sep 2021 • Zezhong Wang, Hongru Wang, Kwan Wai Chung, Jia Zhu, Gabriel Pui Cheong Fung, Kam-Fai Wong
To tackle this problem, we propose an effective similarity-based method to select data from the source domains.
no code implementations • 26 Aug 2021 • Hongru Wang, Zezhong Wang, Wai Chung Kwan, Kam-Fai Wong
Meta-learning is widely used for few-shot slot tagging in task of few-shot learning.
no code implementations • 17 Nov 2020 • Hongru Wang, Min Li, Zimo Zhou, Gabriel Pui Cheong Fung, Kam-Fai Wong
In this paper, we publish a first Cantonese knowledge-driven Dialogue Dataset for REStaurant (KddRES) in Hong Kong, which grounds the information in multi-turn conversations to one specific restaurant.
no code implementations • SEMEVAL 2020 • Hongru Wang, Xiangru Tang, Sunny Lai, Kwong Sak Leung, Jia Zhu, Gabriel Pui Cheong Fung, Kam-Fai Wong
This paper describes our system submitted to task 4 of SemEval 2020: Commonsense Validation and Explanation (ComVE) which consists of three sub-tasks.