Papers by Kyoung-Woon On
How Well Do Large Language Models Truly Ground? (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing research defines “grounding” as having the correct answer, which does not ensure the reliability of the entire response. |
| Approach: | They propose a stricter definition of grounding: fully utilizes the necessary knowledge from the provided context and stays within the limits of that knowledge. |
| Outcome: | The proposed model can be ground on external contexts and maintain its correct answer. |
TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback (2024.findings-acl)
Copied to clipboard
Eunseop Yoon, Hee Suk Yoon, SooHwan Eom, Gunsoo Han, Daniel Nam, Daejin Jo, Kyoung-Woon On, Mark Hasegawa-Johnson, Sungwoong Kim, Chang Yoo
| Challenge: | Existing approaches to provide token-level rewards fail to account for varying degrees of preference inherent to each token. |
| Approach: | They propose a reward model that uses a discriminator to assign token-based continuous rewards to each token considering the context. |
| Outcome: | Extensive experiments show that the proposed reward model improves on open-ended language generation benchmarks. |
Binary Classifier Optimization for Large Language Model Alignment (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for aligning large language models rely on preference-based approaches that require both positive and negative feedback as a pair. |
| Approach: | They propose a binary classifier optimization technique that trains a classifier using only binary feedback and a reward shift technique which minimizes the DPO loss. |
| Outcome: | The proposed method performs on a paired preference dataset and on 'likert-5 scale annotation dataset' it consistently demonstrates effective and robust alignment across four base LLMs and three different datasets, showcasing the strength of the proposed technique. |
Semiparametric Token-Sequence Co-Supervision (2024.acl-long)
Copied to clipboard
| Challenge: | Using semiparametric token-sequence co-supervision, language models are trained using a finite parametric vocabulary space. |
| Approach: | They propose a semiparametric token-sequence co-supervision training method that leverages supervision from two different supervisions. |
| Outcome: | The proposed method outperforms models trained via each supervision independently and shows that it encourages a broader generalization capability across the model. |
Evaluating Legal Reasoning Traces with Legal Issue Tree Rubrics (2026.acl-long)
Copied to clipboard
| Challenge: | Evaluating the quality of LLM-generated reasoning traces in expert domains is essential for ensuring credibility and explainability, yet remains challenging due to the inherent complexity of such reasoning tasks. |
| Approach: | They propose a large-scale legal reasoning dataset with an emphasis on reasoning trace evaluation that converts court judgments into hierarchical trees of opposing parties’ arguments and the court’s conclusions. |
| Outcome: | The proposed model improves the quality of LLM-generated reasoning traces in legal domains, whereas RL improves correctness albeit with reduced coverage. |
Efficient Latent Variable Modeling for Knowledge-Grounded Dialogue Generation (2023.findings-emnlp)
Copied to clipboard
Gunsoo Han, Daejin Jo, Daniel Nam, Eunseop Yoon, Taehwan Kwon, Seungeun Rho, Kyoung-Woon On, Chang Yoo, Sungwoong Kim
| Challenge: | Existing knowledge-grounded dialogue generation algorithms require annotated knowledge to generate a response grounded on the retrieved knowledge. |
| Approach: | They propose an efficient algorithm for latent variable modeling that leverages large amount of dialogue data. |
| Outcome: | The proposed algorithm outperforms the supervised learning algorithm on knowledge-grounded dialogue datasets while maintaining efficiency and scalability. |
Korean Canonical Legal Benchmark: Toward Knowledge-Independent Evaluation of LLMs’ Legal Reasoning Capabilities (2026.eacl-short)
Copied to clipboard
| Challenge: | Large reasoning models trained to reason explicitly in the verbal space have shown superior performance over general large language models (Guo et al., 2025). |
| Approach: | They propose to use Korean Canonical Legal Benchmark to assess language models' legal reasoning capabilities independently of domain-specific knowledge. |
| Outcome: | The proposed benchmark outperforms general-purpose models in a systematic evaluation of 30+ models. |