Papers by Taesup Kim

10 papers
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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations