Papers by Jiwon Kim
LimaCost: Data Valuation for Instruction Tuning of Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Instruction tuning is an effective approach for aligning large language models with human intentions. |
| Approach: | They propose a data quality measure that exhibits a strong correlation with model performance. |
| Outcome: | The proposed measure exhibits a strong correlation with model performance. |
FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) excel at handling long-context sequences, but require substantial prefill computation and key-value (KV) cache. |
| Approach: | They propose a KV cache compression framework that decouples prefill computation from decoding KV budget. |
| Outcome: | The proposed framework reduces latency in prefill and decoding by leveraging the stabilization of token importance in later layers. |
Don’t Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly used as evaluators for code evaluation tasks . however, whether they can handle superficial variations remains unclear . |
| Approach: | They define six types of potential biases in code evaluation and reveal their impact on LLM judges. |
| Outcome: | The proposed method can be used to evaluate semantically equivalent code with superficial variations without reference implementations. |
Speculative Verification: Exploiting Information Gain for Speculative Decoding (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are used for many applications but their size and computational cost make inference serving a significant challenge. |
| Approach: | They propose an efficient augmentation to Speculative Decoding (SD) that predicts speculation accuracy and dynamically adapts the verification length to maximize throughput. |
| Outcome: | The proposed model reduces wasted verification on rejected tokens and improves decoding efficiency. |
X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents (2023.findings-acl)
Copied to clipboard
Mehrad Moradshahi, Tianhao Shen, Kalika Bali, Monojit Choudhury, Gael de Chalendar, Anmol Goel, Sungkyun Kim, Prashant Kodali, Ponnurangam Kumaraguru, Nasredine Semmar, Sina Semnani, Jiwon Seo, Vivek Seshadri, Manish Shrivastava, Michael Sun, Aditya Yadavalli, Chaobin You, Deyi Xiong, Monica Lam
| Challenge: | X-RiSAWOZ dataset has more than 18,000 human-verified dialogue utterances for each language . Xiaoping and Xinhui are the main challenges for task-oriented dialogue research . |
| Approach: | They develop a toolkit to accelerate the post-editing of a new language dataset after translation . their dataset, code, and toolkit are released open-source . |
| Outcome: | The proposed toolkit accelerates the post-editing of a new language dataset after translation. |
Being Kind Isn’t Always Being Safe: Diagnosing Affective Hallucination in LLMs (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly engaged in emotionally vulnerable conversations that extend beyond information seeking to moments of personal distress. |
| Approach: | They propose AHaBench, a benchmark of 500 mental-health-related prompts with expert-informed reference responses, evaluated along three dimensions: Emotional Enmeshment, Illusion of Presence, and Fostering Overdependence. |
| Outcome: | The proposed model is based on 500 mental-health-related prompts with expert-informed reference responses and a 5K-instance preference dataset enabling direct preference optimization (DPO) for alignment with emotionally responsible behavior. |
Joint Multimodal Preference Optimization for Fine-Grained Visual-Textual Alignment (2026.findings-eacl)
Copied to clipboard
| Challenge: | Recent research has focused on addressing multimodal hallucinations in Large Vision-Language Models (LVLMs) however, these methods lack fine-grained visual contrast mechanisms and rely on single-margin optimization. |
| Approach: | They propose a framework that integrates text-conditioned preference loss with visual ranking-based objective. |
| Outcome: | The proposed framework improves cross-modal alignment and fine-grained visual grounding. |