Papers by Taesup Kim
Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Information (2024.findings-naacl)
Copied to clipboard
| Challenge: | Prior studies have attempted to enhance faithfulness of abstractive summarization, yet hallucination remains a persistent challenge. |
| Approach: | They propose a decoding strategy that adjusts the generation probability of each token by comparing it with the token’s marginal probability within the domain of the source text. |
| Outcome: | The proposed method significantly improves faithfulness and source relevance on the XSUM dataset. |
PRISP: Privacy-Safe Few-Shot Personalization via Lightweight Adaptation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for large language model personalization are limited by data-rich settings and privacy risks. |
| Approach: | They propose a lightweight and privacy-safe personalization framework tailored to constraints in large language models. |
| Outcome: | Experiments on a few-shot variant of the LaMP benchmark show that PRISP achieves strong overall performance compared to prior approaches. |
Assessing Socio-Cultural Alignment and Technical Safety of Sovereign LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent trends in LLMs development show growing interest in the use and application of sovereign LLM models. |
| Approach: | They propose a framework for extracting and evaluating socio-cultural elements of sovereign LLMs and assess their technical robustness. |
| Outcome: | The proposed framework assesses the socio-cultural elements of sovereign LLMs and their technical robustness. |
“Well, Keep Thinking”: Enhancing LLM Reasoning with Adaptive Injection Decoding (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) exhibit strong reasoning abilities, often attributed to few-shot or zero-shot Chain-of-Thought (CoT) prompting. |
| Approach: | They propose a decoding strategy that nudges LLMs to continue reasoning, thereby preventing immature reasoning processes. |
| Outcome: | The proposed method significantly improves LLM reasoning capabilities on diverse reasoning benchmarks. |
Stable On-Policy Distillation through Adaptive Target Reformulation (2026.findings-acl)
Copied to clipboard
| Challenge: | Knowledge distillation (KD) is widely used for transferring capabilities from proprietary models to efficient open-source counterparts. |
| Approach: | They propose a method that constructs a geometric target distribution in logit space to emphasize agreement between the teacher and the student. |
| Outcome: | Experiments show that the proposed method outperforms supervised fine-tuning and existing on-policy baselines. |
EpiCaR: Knowing What You Don’t Know Matters for Better Reasoning in LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to improving reasoning abilities of large language models incur a significant calibration cost. |
| Approach: | They propose an epistemic learning problem that integrates reasoning and calibration into an iterative supervised training framework. |
| Outcome: | The proposed method achieves Pareto-superiority over standard baselines in accuracy and calibration. |
Evaluating Structure-Aware Retrieval and Safety in Statute-Centric Legal QA (2026.acl-long)
Copied to clipboard
Kyubyung Chae, Jewon Yeom, Jeongjae Park, Seunghyun Bae, Ijun Jang, Hyunbin Jin, Jinkwan Jang, Taesup Kim
| Challenge: | Legal QA benchmarks focus on case law, overlooking statute-centric regulatory reasoning . relevant evidence is distributed across hierarchically linked documents, creating statutory retrieval gap . |
| Approach: | They propose a structure- and safety-aware benchmark for statute-centric legal QA . the benchmark assesses whether models can retrieve hierarchically fragmented evidence . |
| Outcome: | The proposed benchmark evaluates whether models can retrieve hierarchically fragmented evidence and safely abstain when statutory context is insufficient. |
FAD-X: Fusing Adapters for Cross-lingual Transfer to Low-Resource Languages (2022.aacl-short)
Copied to clipboard
| Challenge: | Adapter-based tuning is a technique that selectively updates language-specific parameters to adapt to a new language, rather than fine-tuning all shared weights. |
| Approach: | They propose to add light-weight adapters to multilingual pretrained language models (mPLMs) and add language-specific parameters to adapt to a new language. |
| Outcome: | The proposed adapter can enhance cross-lingual transfer from pretrained adapters for well-known named entity recognition and classification benchmarks. |
DoMIX: An Efficient Framework for Exploiting Domain Knowledge in Fine-Tuning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for domain-adaptive pre-training (DAP) face several limitations: high computational cost and GPU memory usage during training; and lack of generalized model for all end tasks. |
| Approach: | They propose a domain-adaptive pre-training (DAP) method that uses a representative parameter-efficient fine-tuning method to provide pre-trained models for specific tasks. |
| Outcome: | The proposed method can be extended beyond the DAP setting to standard LLM fine-tuning scenarios. |
Model-based Preference Optimization in Abstractive Summarization without Human Feedback (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can generate fluent summaries but often introduce inaccuracies by hallucinating content not found in the source document. |
| Approach: | They propose a method to fine-tune Large Language Models for improved summarization abilities without any human feedback. |
| Outcome: | The proposed method significantly improves the quality of generated summaries without any human feedback. |