1 citations · 2 across the 6 of their papers we have counts for
7 papers
When Reasoning Traces Conflict with Evidence: How Answer Configuration Shapes Evidence Following
Shaoang Li, Yanhang Shi, Jian Li
A reasoning trace retained at answer time plays two roles: it can raise accuracy, and it can compete with the current evidence when the two disagree. We disentangle these roles by…
Dual-Adversarial Safety Alignment: Cultivating Intrinsic Threat Comprehension in LRMs
Hongli Shen, Shaopeng Fu, Qinbo Zhang +2
Large reasoning models (LRMs) achieve remarkable success on complex tasks but remain vulnerable to harmful prompts that induce unsafe outputs. Recent methods align LRMs using direc…
Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding
Weixu Zhang, Fanghua Ye, Qiang Gao +7
Large language models (LLMs) often produce content that contradicts or overlooks information provided in the input context, a phenomenon known as faithfulness hallucination. In thi…
Learning Evidence Highlighting for Frozen LLMs
Shaoang Li, Yanhang Shi, Yufei Li +10
Large Language Models (LLMs) can reason well, yet often miss decisive evidence when it is buried in long, noisy contexts. We introduce HiLight, an Evidence Emphasis framework that…
Are Large Language Models Good Prompt Optimizers?
Ruotian Ma, Xiaolei Wang, Xin Zhou +5
LLM-based Automatic Prompt Optimization, which typically utilizes LLMs as Prompt Optimizers to self-reflect and refine prompts, has shown promising performance in recent studies. D…
Look Before You Leap: Towards Decision-Aware and Generalizable Tool-Usage for Large Language Models
Anchun Gui, Jian Li, Yong Dai +2
Tool-augmented large language models (LLMs) are attracting widespread attention when accessing up-to-date knowledge and alleviating hallucination issues. Nowadays, advanced closed-…
Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game
Pengyu Cheng, Yifan Yang, Jian Li +5
Human preference alignment is essential to improve the interaction quality of large language models (LLMs). Existing alignment methods depend on manually annotated preference data…