From the 1 of 41 linked papers with an AI index.
28 papers · 1 filter
Hi-TTRL: Regulating Consensus with Hints for Test-Time Reinforcement Learning
Kunbin Xu, Xingzuo Li, Xuefeng Bai +1
Test-time reinforcement learning (TTRL) improves the reasoning capabilities of large language models without labeled data by updating the policy with pseudo-labels constructed thro…
DualAnchor: Preserving Language Priors and Improving Lexical Fidelity in Gloss-Free Sign Language Translation
Hongbin Zhang, Junhao Liu, Xuefeng Bai +3
The paper introduces DualAnchor, a training framework for gloss-free sign language translation that preserves large language model priors with token-level prior anchoring and enhan…
Agentic Tool Use in Large Language Models
Jinchao Hu, Meizhi Zhong, Kehai Chen +2
Large language models are increasingly being deployed as autonomous agents yet their real world effectiveness depends on reliable tools for information retrieval, computation and e…
Instruction Anchor: Dissecting the Mechanistic Dynamics of Modality Arbitration
Yu Zhang, Mufan Xu, Xuefeng Bai +4
Modality following is the ability to selectively leverage multimodal contexts based on user instructions. It is fundamental to the safety and reliability of multimodal large langua…
Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck
Hongbin Zhang, Kehai Chen, Xuefen Bai +4
Large language models (LLMs) have become a standard for multilingual evaluation, yet they exhibit a severe systematic translationese bias. In this paper, translationese bias is cha…
Beyond Token-Level Policy Gradients for Complex Reasoning with Large Language Models
Mufan Xu, Kehai Chen, Xuefeng Bai +4
Existing policy-gradient methods for auto-regressive language models typically select subsequent tokens one at a time as actions in the policy. While effective for many generation…