9 citations · 10 across the 7 of their papers we have counts for
7 papers
FARS: A Fully Automated Research System Deployed at Scale
Qiong Tang, Tianxiang Sun, Xiangkun Hu +54
Recent automated research systems show that language-model agents can generate hypotheses, run experiments, and write complete manuscripts, but most evidence still comes from selec…
NLL-Guided Full-Attention Layer Selection for Training-Free Sliding-Window Adaptation
Qiong Tang, Xiangkun Hu, Xiangyang Liu +2
Hybrid attention models that mix full and sliding-window attention across layers offer a promising approach to efficient long-context inference, but the critical question of \emph{…
Output-Space Allocation Costs for Calibration-Guided LLM Compression: An Empirical Study
Qiong Tang, Xiangkun Hu, Xiangyang Liu +2
Training-free compression methods for large language models (LLMs) often use calibration data to guide compression decisions. ROCKET, a recent method combining sparse-dictionary fa…
Explicit Preference Optimization: No Need for an Implicit Reward Model
Xiangkun Hu, Lemin Kong, Tong He +1
The generated responses of large language models (LLMs) are often fine-tuned to human preferences through a process called reinforcement learning from human feedback (RLHF). As RLH…
Quantifying Fairness in LLMs Beyond Tokens: A Semantic and Statistical Perspective
Weijie Xu, Yiwen Wang, Chi Xue +4
Large Language Models (LLMs) often generate responses with inherent biases, undermining their reliability in real-world applications. Existing evaluation methods often overlook bia…
RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation
Dongyu Ru, Lin Qiu, Xiangkun Hu +15
Despite Retrieval-Augmented Generation (RAG) showing promising capability in leveraging external knowledge, a comprehensive evaluation of RAG systems is still challenging due to th…
New Desiderata for Direct Preference Optimization
Xiangkun Hu, Tong He, David Wipf
Large language models in the past have typically relied on some form of reinforcement learning with human feedback (RLHF) to better align model responses with human preferences. Ho…