Papers by Wenjie Yin
Finding RELIEF: Shaping Reasoning Behavior without Reasoning Supervision via Belief Engineering (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for shaping large reasoning models rely on reinforcement learning or fine-tuning with gold-standard reasoning traces. Existing techniques for behavior shaping rely only on additional reward modeling. |
| Approach: | They propose a framework that aligns a model's self-concept with a target belief blueprint and internalizes desired traits by fine-tuning on synthesized, self-reflective QA pairs that affirm the target belief. |
| Outcome: | The proposed framework outperforms behavior-supervised and preference-based models while requiring significantly lower training costs. |
ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation (2025.emnlp-main)
Copied to clipboard
Minghua He, Yue Chen, Fangkai Yang, Pu Zhao, Wenjie Yin, Yu Kang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
| Challenge: | Existing code translation models only learn the contextual semantics of code during pre-training, neglecting executability information closely related to the execution state of the code. |
| Approach: | They propose an LLM specifically designed for code translation called ExeCoder . it uses executability representations such as functional semantics and syntax structures to enhance LLMs' capabilities. |
| Outcome: | The proposed model outperforms existing open-source code translation models on two metrics. |
Why Safeguarded Ships Run Aground? Aligned Large Language Models’ Safety Mechanisms Tend to Be Anchored in The Template Region (2025.acl-long)
Copied to clipboard
| Challenge: | Infilling a fixed template between the input instruction and initial model output is a common practice for existing LLMs, but it is vulnerable to inference-time jailbreak attacks. |
| Approach: | They propose to fill a fixed template between the input instruction and initial model output and to detach safety mechanisms from the template region to mitigate the risk of inference-time jailbreak attacks. |
| Outcome: | The proposed method is widespread across aligned LLMs and shows that it mitigates inference-time jailbreak vulnerabilities. |
GOVERN: Gradient Orientation Vote Ensemble for Multi-Teacher Reinforced Distillation (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Pre-trained language models have achieved remarkable performance in OpenQA, but for practical deployment, knowledge distillation is crucial to maintain high performance while operating under computational constraints. |
| Approach: | They propose an algorithm to perform unsupervised knowledge distillation without the guidance of labels to achieve 99.5% of performance. |
| Outcome: | The proposed algorithm achieves 99.5% of performance in a commercial question-answering system. |