8 citations · 30 across the 20 of their papers we have counts for
20 papers
Write, Execute, Refine: From Skill Follower to Skill Optimizer via Reinforcement Learning from Execution Feedback
Kang Peng, Zhiwei Zhang, Yichen Zhang +7
Expert-written natural language skills can improve tool-using agents, yet agent-authored skills perform 8--11 points worse than using no skill. While inference-time loops can repai…
Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models
Zhengyi Zhao, Shubo Zhang, Huimin Wang +7
Large Reasoning Models (LRMs) have demonstrated impressive capabilities in many tasks, yet they struggle with reliably following multiple instructions, either by failing to satisfy…
Beyond the Literal: Decomposing Pragmatic Intent in Multimodal Meme Understanding
Zhengyi Zhao, Shubo Zhang, Zezhong Wang +6
When asked what a meme or sarcastic post means, Large Vision Language Models (LVLMs) tend to describe what the image shows rather than what the author is trying to communicate. Sta…
Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation
Zhengyi Zhao, Shubo Zhang, Zezhong Wang +7
Retrieval-Augmented Generation (RAG) significantly enhances Large Language Models (LLMs) by providing access to external knowledge. However, current research primarily focuses on r…
Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors
Zhiwei Zhang, Fei Zhao, Rui Wang +6
Large language models (LLMs) can call tools effectively, yet they remain brittle in multi-turn execution: after a tool-call error, smaller models often fall into repetitive invalid…
MemeReaCon: Probing Contextual Meme Understanding in Large Vision-Language Models
Zhengyi Zhao, Shubo Zhang, Yuxi Zhang +10
Memes have emerged as a popular form of multimodal online communication, where their interpretation heavily depends on the specific context in which they appear. Current approaches…
T: An Adaptive Test-Time Scaling Strategy for Contextual Question Answering
Zhengyi Zhao, Shubo Zhang, Zezhong Wang +7
Recent advances in Large Language Models (LLMs) have demonstrated remarkable performance in Contextual Question Answering (CQA). However, prior approaches typically employ elaborat…
Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs' Reasoning
Zezhong Wang, Xingshan Zeng, Weiwen Liu +7
Mathematical reasoning through Chain-of-Thought (CoT) has emerged as a powerful capability of Large Language Models (LLMs), which can be further enhanced through Test-Time Scaling…
FReM: A Flexible Reasoning Mechanism for Balancing Quick and Slow Thinking in Long-Context Question Answering
Zhengyi Zhao, Shubo Zhang, Zezhong Wang +3
Long-context question-answering (LCQA) systems have greatly benefited from the powerful reasoning capabilities of large language models (LLMs), which can be categorized into slow a…
Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step
Zezhong Wang, Xingshan Zeng, Weiwen Liu +7
Current research found the issue of Early Answering in large language models (LLMs), where the models already have an answer before generating the Chain-of-Thought (CoT). This phen…
PerLTQA: A Personal Long-Term Memory Dataset for Memory Classification, Retrieval, and Synthesis in Question Answering
Yiming Du, Hongru Wang, Zhengyi Zhao +5
Long-term memory plays a critical role in personal interaction, considering long-term memory can better leverage world knowledge, historical information, and preferences in dialogu…
UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systems
Hongru Wang, Wenyu Huang, Yang Deng +6
Large Language Models (LLMs) has shown exceptional capabilities in many natual language understanding and generation tasks. However, the personalization issue still remains a much-…
Self-Guard: Empower the LLM to Safeguard Itself
Zezhong Wang, Fangkai Yang, Lu Wang +5
The jailbreak attack can bypass the safety measures of a Large Language Model (LLM), generating harmful content. This misuse of LLM has led to negative societal consequences. Curre…
JoTR: A Joint Transformer and Reinforcement Learning Framework for Dialog Policy Learning
Wai-Chung Kwan, Huimin Wang, Hongru Wang +4
Dialogue policy learning (DPL) is a crucial component of dialogue modelling. Its primary role is to determine the appropriate abstract response, commonly referred to as the "dialog…
Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularization
Liang Chen, Hongru Wang, Yang Deng +3
Generating persona consistent dialogue response is important for developing an intelligent conversational agent. Recent works typically fine-tune large-scale pre-trained models on…
Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs
Hongru Wang, Rui Wang, Fei Mi +5
Large Language Models (LLMs), such as \texttt{ChatGPT}, greatly empower dialogue systems with strong language understanding and generation capabilities. However, most of the previo…
Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering
Fangkai Yang, Pu Zhao, Zezhong Wang +6
Large Language Model (LLM) has gained popularity and achieved remarkable results in open-domain tasks, but its performance in real industrial domain-specific scenarios is average d…
Integrating Pretrained Language Model for Dialogue Policy Learning
Hongru Wang, Huimin Wang, Zezhong Wang +1
Reinforcement Learning (RL) has been witnessed its potential for training a dialogue policy agent towards maximizing the accumulated rewards given from users. However, the reward c…
Prior Omission of Dissimilar Source Domain(s) for Cost-Effective Few-Shot Learning
Zezhong Wang, Hongru Wang, Kwan Wai Chung +3
Few-shot slot tagging is an emerging research topic in the field of Natural Language Understanding (NLU). With sufficient annotated data from source domains, the key challenge is h…
MCML: A Novel Memory-based Contrastive Meta-Learning Method for Few Shot Slot Tagging
Hongru Wang, Zezhong Wang, Wai Chung Kwan +1
Meta-learning is widely used for few-shot slot tagging in task of few-shot learning. The performance of existing methods is, however, seriously affected by \textit{sample forgettin…