collaborators

11 papers

cs.CL2026

Towards End-to-End Multilingual Metaphor Processing: Integrating Detection, Translation, and Evaluation

Jiahui Liang, Lifeng Han

Metaphorical language remains a major challenge for multilingual natural language processing because successful interpretation and translation require reasoning beyond literal lexi…

cs.CL2026

MetaHOPE: A Metaphor-Oriented Evaluation Framework for Analysing MT and LLM Translation Errors

Jiahui Liang, Lifeng Han

In this opinion paper, we propose MetaHOPE, an error severity-aware annotation framework for evaluating metaphor translations. Metaphors present challenges for machine translation…

cs.AI2026

Woodpecker Distillation: Weak Models Diagnose Reasoning Bugs in Strong Models

Dayu Wang, Jiaye Yang, Weikang Li +4

Large language models often fail on reasoning tasks despite possessing the capability to solve them. We argue that many such failures arise from localized reasoning bugs in interme…

cs.SE2026

One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents

Zhaoxi Zhang, Yitong Duan, Yanzhi Zhang +9

Locating files and functions requiring modification in large software repositories is challenging due to their scale and structural complexity. Existing LLM-based methods typically…

cs.SE2026

RepoZero: Can LLMs Generate a Code Repository from Scratch?

Zhaoxi Zhang, Yiming Xu, Jiahui Liang +7

Large Language Models (LLMs) have recently shown remarkable progress in code generation, yet their ability to construct complete software repositories from scratch remains poorly u…

cs.AI2026

It Takes 8 Tokens: Weak-to-Strong Off-Policy RL via Auxiliary Branches

Dayu Wang, Jiaye Yang, Weikang Li +4

Reinforcement learning with verifiable rewards has emerged as a standard approach for enhancing reasoning in large language models, which typically optimizes the policy by contrast…