Papers by Hyokun Yun
Do LLMs Catch Their Own Mistakes? A Comprehensive Benchmark for Reflective Tool Use LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks primarily evaluate planning and execution success, overlooking the self-reflective dimension of tool use. |
| Approach: | They propose a benchmark to assess LLMs’ self-reflective reasoning in tool-augmented multi-turn dialogues. |
| Outcome: | The proposed benchmark covers 10 domains with 88 distinct APIs and 968 annotated dialogues, systematically injecting diverse error types arising from both user and assistant behavior. |
Aligning Large Language Models with Implicit Preferences from User-Generated Content (2025.acl-long)
Copied to clipboard
Zhaoxuan Tan, Zheng Li, Tianyi Liu, Haodong Wang, Hyokun Yun, Ming Zeng, Pei Chen, Zhihan Zhang, Yifan Gao, Ruijie Wang, Priyanka Nigam, Bing Yin, Meng Jiang
| Challenge: | Existing preference learning methods rely heavily on curated data from humans or advanced LLMs, which is costly and difficult to scale. |
| Approach: | They propose a framework that leverages implicit preferences in unlabeled user-generated content to generate preference data. |
| Outcome: | The proposed framework transforms user-generated content into user queries and generates responses from the policy model. |
AutoMixAlign: Adaptive Data Mixing for Multi-Task Preference Optimization in LLMs (2025.acl-long)
Copied to clipboard
Nicholas E. Corrado, Julian Katz-Samuels, Adithya M Devraj, Hyokun Yun, Chao Zhang, Yi Xu, Yi Pan, Bing Yin, Trishul Chilimbi
| Challenge: | Existing approaches to align large language models rely on large ablation studies, heuristics, or human intuition to produce models with strong performance across tasks. |
| Approach: | They propose an algorithm that mixes datasets during LLM training to balance performance across multiple tasks. |
| Outcome: | The proposed algorithm outperforms existing methods on multitask alignment setups and achieves convergence rate of O(1/T) in the convex case. |
Evolutionary Contrastive Distillation for Language Model Alignment (2024.findings-emnlp)
Copied to clipboard
Julian Katz-Samuels, Zheng Li, Hyokun Yun, Priyanka Nigam, Yi Xu, Vaclav Petricek, Bing Yin, Trishul Chilimbi
| Challenge: | Existing studies indicate that large language models struggle with challenging instructions. |
| Approach: | They propose a method for generating high-quality synthetic preference data to enhance the complex instruction-following capability of language models. |
| Outcome: | The proposed method exceeds the performance of current SOTA 7B models and is competitive even with open-source 70B models. |
WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning (2025.emnlp-main)
Copied to clipboard
Zhepei Wei, Wenlin Yao, Yao Liu, Weizhi Zhang, Qin Lu, Liang Qiu, Changlong Yu, Puyang Xu, Chao Zhang, Bing Yin, Hyokun Yun, Lihong Li
| Challenge: | Existing work on reinforcement learning has focused on single-turn tasks such as solving math problems. |
| Approach: | They propose a framework that learns directly from online interactions by asynchronously generating diverse trajectories, guided by binary rewards depending on task success. |
| Outcome: | Experiments on the WebArena-Lite benchmark show that the framework outperforms state-of-the-art methods and strong proprietary models. |
DORM: Preference Data Weights Optimization for Reward Modeling in LLM Alignment (2025.findings-emnlp)
Copied to clipboard
Rongzhi Zhang, Chenwei Zhang, Xinyang Zhang, Liang Qiu, Haoming Jiang, Yuchen Zhuang, Qingru Zhang, Hyokun Yun, Xian Li, Bing Yin, Tuo Zhao, Chao Zhang
| Challenge: | Existing approaches to align large language models with human preferences are noisy and varying in importance of preference samples. |
| Approach: | a new method enhances reward modeling by learning to dynamically weigh preference data. |
| Outcome: | a new method improves the performance of large language models with human preferences . it initializes data importance and iteratively refines them to maximize validation performance. |
MICO: Selective Search with Mutual Information Co-training (2022.coling-1)
Copied to clipboard
| Challenge: | Selective search is designed to reduce the latency and computation in modern large-scale search systems. |
| Approach: | They propose a mutual information CO-training framework for selective search with minimal supervision using the search logs. |
| Outcome: | The proposed framework outperforms existing competitive benchmarks on multiple metrics and significantly outperformed existing baselines. |
Robustness to Capitalization Errors in Named Entity Recognition (D19-55)
Copied to clipboard
| Challenge: | Existing methods to improve robustness to noise discard given orthographic information, which significantly degrades models' performance on well-formed text. |
| Approach: | They propose a method which allows models to learn to utilize or ignore orthographic information depending on its usefulness in the context. |
| Outcome: | The proposed approach achieves competitive robustness to capitalization errors while making negligible compromises on well-formed text and significantly improving generalization power on noisy user-generated text. |