From the 1 of 9 linked papers with an AI index.
9 papers
Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis
Xinhao Yao, Yuanzhuo Liu, Changhao Wang +6
Deep search is becoming a core capability of modern agent systems, yet it is typically evaluated solely based on end-to-end answer accuracy. This coupled evaluation paradigm entang…
UXBench: Benchmarking User Experience in AI Assistants
Mengze Hong, Xia Zeng, Zeyang Lei +26
UXBench is a user‑centric benchmark that uses real interaction logs to evaluate how well AI assistants align with user preferences and generate engaging dialogue, featuring three t…
TRACE: Discovering Task-Specific Parameter via Adaptation-Aware Probing for Continual Fine-Tuning
Xiaosong Han, Ke Chen, Xindi Dai +7
In real-world deployment, LLMs are often adapted continually across tasks to keep LLMs up-to-date in production, where new fine-tuning should preserve previously learned skills. Ho…
Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty
Chao Xue, Yao Wang, Mengqiao Liu +11
Recent advancements in the Generative Reward Model (GRM) have demonstrated its potential to enhance the reasoning abilities of LLMs through Chain-of-Thought (CoT) prompting. Despit…
Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models
Chao Xue, Yao Wang, Mengqiao Liu +11
Supervised Fine-Tuning (SFT) is the standard approach for adapting large language models (LLMs) to downstream tasks. However, we observe a persistent failure mode: even after conve…
Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning
Zekai Lin, Chao Xue, Di Liang +8
Supervised Fine-Tuning (SFT) of large language models often suffers from task interference and catastrophic forgetting. Recent approaches alleviate this issue by isolating task-cri…