Papers by Jonghyun Choi
Representation Bending for Large Language Model Safety (2025.acl-long)
Copied to clipboard
Ashkan Yousefpour, Taeheon Kim, Ryan Sungmo Kwon, Seungbeen Lee, Wonje Jeung, Seungju Han, Alvin Wan, Harrison Ngan, Youngjae Yu, Jonghyun Choi
| Challenge: | Existing safety-enhancing techniques, such as fine-tuning with human feedback or adversarial training, are still vulnerable as they address specific threats and fail to generalize across unseen attacks. |
| Approach: | They propose a new approach that disrupts representations underlying harmful behaviors in Large Language Models by using loss-based fine-tuning. |
| Outcome: | The proposed approach outperforms existing methods such as Circuit Breaker, RMU, and NPO with 95% reduction in attack success rates across diverse jailbreak benchmarks. |
Iconary: A Pictionary-Based Game for Testing Multimodal Communication with Drawings and Text (2021.emnlp-main)
Copied to clipboard
Christopher Clark, Jordi Salvador, Dustin Schwenk, Derrick Bonafilia, Mark Yatskar, Eric Kolve, Alvaro Herrasti, Jonghyun Choi, Sachin Mehta, Sam Skjonsberg, Carissa Schoenick, Aaron Sarnat, Hannaneh Hajishirzi, Aniruddha Kembhavi, Oren Etzioni, Ali Farhadi
| Challenge: | Communicating with humans is challenging for AIs because of its complexity and multimodality. |
| Approach: | They propose to use a game of drawing and guessing based on Pictionary to test AIs' understanding of the world and multi-modal gestures. |
| Outcome: | The proposed game is a test for mixing language and visual/symbolic communication in AI. |
OASIS: Online Sample Selection for Continual Instruction Tuning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for continual instruction tuning (CIT) use pre-trained reference models, which are impractical in CIT setups since future data are unknown. |
| Approach: | They propose an adaptive online sample selection approach that estimates each sample’s informativeness relative to all previously seen data and minimizes informative redundancy through iterative selection score updates. |
| Outcome: | Experiments on various large foundation models show that using only 25% of the data achieves comparable performance to full-data training and outperforms the state-of-the-art sampling methods. |
Becoming Experienced Judges: Selective Test-Time Learning for Evaluators (2026.eacl-short)
Copied to clipboard
| Challenge: | Large language models and visionlanguage models are increasingly used as automatic evaluators. |
| Approach: | They propose a framework that allows evaluators to improve *sequentially* at inference time without additional training or external signals. |
| Outcome: | The proposed framework outperforms strong baselines in two pairwise comparisons. |
Large Language Models Still Exhibit Bias in Long Text (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing fairness benchmarks for large language models focus on simple tasks . a new framework evaluates biases in LLMs through essay-style prompts . |
| Approach: | They propose a framework that evaluates biases in large language models through essay-style prompts. |
| Outcome: | The proposed framework uncovers subtle biases difficult to detect in simple responses. |
Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback (2024.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models have influenced the development of video large multimodal models (VLMMs). |
| Approach: | They propose a method that integrates video descriptions as context into a multimodal AI system to enrich the understanding of video content. |
| Outcome: | Empirical evaluations show that the proposed approach outperforms existing approaches for video large multimodal models (VLMMs) |