6 papers
Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents
Yiming Du, Baojun Wang, Yifan Xiang +11
Temporal reasoning over long, multi-session dialogues is a critical capability for conversational agents. However, existing works and our pilot study have shown that as dialogue hi…
ToolACE: Winning the Points of LLM Function Calling
Weiwen Liu, Xu Huang, Xingshan Zeng +24
Function calling significantly extends the application boundary of large language models, where high-quality and diverse training data is critical for unlocking this capability. Ho…
ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis
Zezhong Wang, Xingshan Zeng, Weiwen Liu +6
Supervised fine-tuning (SFT) is a common method to enhance the tool calling capabilities of Large Language Models (LLMs), with the training data often being synthesized. The curren…
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…
Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization
Yuxin Jiang, Bo Huang, Yufei Wang +7
Direct preference optimization (DPO), a widely adopted offline preference optimization algorithm, aims to align large language models (LLMs) with human-desired behaviors using pair…
Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models
Lingzhi Wang, Xingshan Zeng, Jinsong Guo +2
This paper explores Machine Unlearning (MU), an emerging field that is gaining increased attention due to concerns about neural models unintentionally remembering personal or sensi…