21 citations · 75 across the 32 of their papers we have counts for
14 papers · 1 filter
OpenReward: Learning to Reward Long-form Agentic Tasks via Reinforcement Learning
Ziyou Hu, Zhengliang Shi, Minghang Zhu +5
Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both training and inference. However, exist…
Social Welfare Function Leaderboard: When LLM Agents Allocate Social Welfare
Zhengliang Shi, Ruotian Ma, Jen-tse Huang +14
Large language models (LLMs) are increasingly entrusted with high-stakes decisions that affect human welfare. However, the principles and values that guide these models when distri…
Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems
Minghang Zhu, Zhengliang Shi, Zhiwei Xu +5
The advancement of large language models (LLMs) has enabled the construction of multi-agent systems to solve complex tasks by dividing responsibilities among specialized agents, su…
Disentangling Knowledge Representations for Large Language Model Editing
Mengqi Zhang, Zisheng Zhou, Xiaotian Ye +4
Knowledge Editing has emerged as a promising solution for efficiently updating embedded knowledge in large language models (LLMs). While existing approaches demonstrate effectivene…
Self-Adaptive Cognitive Debiasing for Large Language Models in Decision-Making
Yougang Lyu, Shijie Ren, Yue Feng +4
Large language models (LLMs) have shown potential in supporting decision-making applications, particularly as personal assistants in the financial, healthcare, and legal domains. W…
UIPE: Enhancing LLM Unlearning by Removing Knowledge Related to Forgetting Targets
Wenyu Wang, Mengqi Zhang, Xiaotian Ye +3
Large Language Models (LLMs) inevitably acquire harmful information during training on massive datasets. LLM unlearning aims to eliminate the influence of such harmful information…
Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models
Zhengliang Shi, Yuhan Wang, Lingyong Yan +4
Tool learning aims to augment large language models (LLMs) with diverse tools, enabling them to act as agents for solving practical tasks. Due to the limited context length of tool…
ASLoRA: Adaptive Sharing Low-Rank Adaptation Across Layers
Junyan Hu, Xue Xiao, Mengqi Zhang +4
As large language models (LLMs) grow in size, traditional full fine-tuning becomes increasingly impractical due to its high computational and storage costs. Although popular parame…
MEFT: Memory-Efficient Fine-Tuning through Sparse Adapter
Jitai Hao, WeiWei Sun, Xin Xin +4
Parameter-Efficient Fine-tuning (PEFT) facilitates the fine-tuning of Large Language Models (LLMs) under limited resources. However, the fine-tuning performance with PEFT on comple…
Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering
Zhengliang Shi, Weiwei Sun, Shen Gao +3
Multi-Hop Question Answering (MHQA) tasks present a significant challenge for large language models (LLMs) due to the intensive knowledge required. Current solutions, like Retrieva…
Learning to Use Tools via Cooperative and Interactive Agents
Zhengliang Shi, Shen Gao, Xiuyi Chen +7
Tool learning empowers large language models (LLMs) as agents to use external tools and extend their utility. Existing methods employ one single LLM-based agent to iteratively sele…
MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-Tuning
Pengjie Ren, Chengshun Shi, Shiguang Wu +5
Parameter-efficient fine-tuning (PEFT) is a popular method for tailoring pre-trained large language models (LLMs), especially as the models' scale and the diversity of tasks increa…
Self-Supervised Position Debiasing for Large Language Models
Zhongkun Liu, Zheng Chen, Mengqi Zhang +3
Fine-tuning has been demonstrated to be an effective method to improve the domain performance of large language models (LLMs). However, LLMs might fit the dataset bias and shortcut…
Multi-Defendant Legal Judgment Prediction via Hierarchical Reasoning
Yougang Lyu, Jitai Hao, Zihan Wang +6
Multiple defendants in a criminal fact description generally exhibit complex interactions, and cannot be well handled by existing Legal Judgment Prediction (LJP) methods which focu…