activity
20242026
collaborators

5 papers

cs.CL2026

To Reason or to Fabricate: Reasoning Without Shortcuts via Hint-Anchored Pairwise Aggregation

Jiuheng Lin, Chen Zhang, Yansong Feng

While reinforcement learning (RL) significantly enhances LLM reasoning, its efficacy is severely undermined by Pre-RL data overlap, where RL datasets overlap with pretraining or SF…

cs.CL2026

CLARity: Reasoning Consistency Alone Can Teach Reinforced Experts

Jiuheng Lin, Cong Jiang, Zirui Wu +2

Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice questions (MCQs). However, standard outcome-based reinforcement learning (RL) on MCQ…

cs.CL2026

Efficient Low-Resource Language Adaptation via Multi-Source Dynamic Logit Fusion

Chen Zhang, Jiuheng Lin, Zhiyuan Liao +1

Adapting large language models (LLMs) to low-resource languages (LRLs) is constrained by the scarcity of task data and computational resources. Although Proxy Tuning offers a logit…

cs.CL2025

Read it in Two Steps: Translating Extremely Low-Resource Languages with Code-Augmented Grammar Books

Chen Zhang, Jiuheng Lin, Xiao Liu +2

While large language models (LLMs) have shown promise in translating extremely low-resource languages using resources like dictionaries, the effectiveness of grammar books remains…

cs.CL2024

Chain of Condition: Construct, Verify and Solve Conditions for Conditional Question Answering

Jiuheng Lin, Yuxuan Lai, Yansong Feng

Conditional question answering (CQA) is an important task that aims to find probable answers and identify missing conditions. Existing approaches struggle with CQA due to two chall…