Papers by Jiuheng Lin
English as Defense Proxy: Mitigating Multilingual Jailbreak via Eliciting English Safety Knowledge (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models excel in many tasks, but their safety guarantees vary by language. |
| Approach: | They propose a unified approach that leverages English as a universal safety anchor. |
| Outcome: | The proposed approach leverages English as defense proxy (E-Proxy) to transfer safety knowledge across languages. |
How Many Answers Should I Give? An Empirical Study of Multi-Answer Reading Comprehension (2023.findings-acl)
Copied to clipboard
| Challenge: | Despite recent progress in multi-answer MRC, there is no systematic analysis of how this phenomenon arises and how to better address it. |
| Approach: | They develop a taxonomy to categorize commonly-seen multi-answer MRC instances and examine how well different paradigms deal with different types of multi-announced questions. |
| Outcome: | The proposed taxonomy categorizes commonly-seen multi-answer instances and analyzes how well different paradigms deal with different types of multi-announced instances. |
MC2: Towards Transparent and Culturally-Aware NLP for Minority Languages in China (2024.acl-long)
Copied to clipboard
| Challenge: | MC2 is the largest open-source corpus of minority languages in china . MC2, however, includes four underrepresented languages: Tibetan, Uyghur, Kazakh, and Mongolian . |
| Approach: | They propose a multilingual corpus of minority languages in China that includes four underrepresented languages . they prioritize accuracy while enhancing diversity by using a quality-centric approach . |
| Outcome: | The proposed model prioritizes accuracy while enhancing diversity, the authors say . MC2 includes four underrepresented languages: Tibetan, Uyghur, Kazakh, and Mongolian . |
Chain of Condition: Construct, Verify and Solve Conditions for Conditional Question Answering (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for conditional question answering struggle with finding probable answers and identifying missing conditions. |
| Approach: | They propose a conditional question answering prompting approach that first identifies all conditions and constructs their logical relationships explicitly according to the document, then verifyes whether these conditions are satisfied and finally solves the logical expression to indicate any missing conditions. |
| Outcome: | The proposed method outperforms existing prompting baselines on two CQA benchmark datasets and can facilitate GPT-3.5-Turbo or GPT-4 to outperFORM all existing supervised models. |
CLARity: Reasoning Consistency Alone Can Teach Reinforced Experts (2026.acl-long)
Copied to clipboard
| Challenge: | Existing solutions to supervise the reasoning process are prohibitively expensive. |
| Approach: | They propose a cost-effective reinforcement learning framework that enhances reasoning quality using a small, general-purpose LLM only. |
| Outcome: | Experiments show that CLARity improves reasoning quality by 16.5% over standard outcome-based reinforcement learning (RL) human evaluations confirm substantial gains in factual correctness and reasoning coherence, leading to more trustworthy model outputs. |
Read it in Two Steps: Translating Extremely Low-Resource Languages with Code-Augmented Grammar Books (2025.acl-long)
Copied to clipboard
| Challenge: | Using code rules improves rule retrieval and application of grammar books in low-resource languages. |
| Approach: | They propose to decompose a grammar rule retrieval and application step into two steps . they propose to represent grammar rules as code functions to facilitate LLM reasoning . |
| Outcome: | The proposed model significantly boosts rule retrieval and application, resulting in 13.1% BLEU improvement. |
Efficient Low-Resource Language Adaptation via Multi-Source Dynamic Logit Fusion (2026.acl-long)
Copied to clipboard
| Challenge: | Proxy Tuning offers a logit-level strategy for introducing scaling effects, but it often fails in LRL settings because the large model’s weak LRL competence might overwhelm the knowledge of specialized smaller models. |
| Approach: | They propose a logit-based framework that balances LRL competence from a continually pretrained small model, task competence from high-resource language instruction tuning, and the scaling benefits of large models. |
| Outcome: | Experiments across four model families and eight LRLs show that TriMix outperforms single-model baselines and Proxy Tuning. |
Teaching Large Language Models an Unseen Language on the Fly (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing large language models struggle to support numerous low-resource languages . Existing models lack sufficient training data for effective parameter updating . |
| Approach: | They propose a framework for adapting LLMs to unseen languages by in-context learning. |
| Outcome: | The proposed framework improves Chinese-to-Zhuang translation performance and Zhuan-to Chinese translation performance. |