Papers by Taeuk Kim
Heads-up! Unsupervised Constituency Parsing via Self-Attention Heads (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing approaches to analyze syntactic knowledge of pre-trained language models have been limited. |
| Approach: | They propose an unsupervised method that extracts constituency trees from PLM attention heads. |
| Outcome: | The proposed method outperforms existing approaches if no development set is present. |
When to Speak, When to Abstain: Contrastive Decoding with Abstention (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) demonstrate exceptional performance across diverse tasks by leveraging pre-trained (parametric) and external (contextual) knowledge. |
| Approach: | They propose a training-free decoding method that allows LLMs to generate responses when relevant knowledge is available and to abstain otherwise. |
| Outcome: | The proposed method can generate responses when relevant knowledge is available and abstain otherwise. |
Memorization or Reasoning? Exploring the Idiom Understanding of LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | idioms have long posed a challenge due to their unique linguistic properties, which set them apart from other common expressions. |
| Approach: | They propose to use a large-scale dataset of idioms in six languages to evaluate LLMs' idiomatic processing ability. |
| Outcome: | The proposed model integrates contextual cues and reasoning to improve idiom understanding in LLMs, suggesting that their performance is influenced by memorization and reasoning. |
Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts (2024.findings-emnlp)
Copied to clipboard
Youna Kim, Hyuhng Joon Kim, Cheonbok Park, Choonghyun Park, Hyunsoo Cho, Junyeob Kim, Kang Min Yoo, Sang-goo Lee, Taeuk Kim
| Challenge: | Recent research has been developed to amplify contextual knowledge over parametric knowledge of large language models (LLMs) in knowledge-intensive tasks such as open-domain question-answering . |
| Approach: | They propose to amplify contextual knowledge over parametric knowledge of large language models (LLMs) by contrastive decoding to leverage contextual influence effectively. |
| Outcome: | The proposed approach improves open-domain question answering tasks especially in robustness by remaining undistracted by noisy contexts in retrieval-augmented generation. |
OMHBench: Benchmarking Balanced and Grounded Omni-Modal Multi-Hop Reasoning (2026.findings-acl)
Copied to clipboard
Seunghee Kim, Ingyu Bang, Seokgyu Jang, Changhyeon Kim, Sanghwan Bae, Jihun Choi, Richeng Xuan, Taeuk Kim
| Challenge: | Existing evaluation frameworks for multimodal large language models suffer from limitations . modality shortcuts and biased reasoning paths are common in such models . |
| Approach: | a new benchmark evaluates omni-modal multi-hop reasoning using 6,144 questions . authors propose OMHBench to address these limitations by comparing modalities . |
| Outcome: | OMHBench evaluates omni-modal multi-hop reasoning on 6,144 questions with balanced reasoning paths . evaluation of 13 state-of-the-art models shows performance gap exists between MLLMs and open-source models . |
Multilingual Chart-based Constituency Parse Extraction from Pre-trained Language Models (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for extracting complete (binary) parses from pre-trained language models are expensive and time-consuming. |
| Approach: | They propose a chart-based method and an effective top-K ensemble technique to extractbinary parses from PLMs. |
| Outcome: | The proposed method can induce non-trivial parses for sentences from nine languages in an integrated and language-agnostic manner, and is robust to cross-lingual transfer. |
Aligning Language Models to Explicitly Handle Ambiguity (2024.emnlp-main)
Copied to clipboard
Hyuhng Joon Kim, Youna Kim, Cheonbok Park, Junyeob Kim, Choonghyun Park, Kang Min Yoo, Sang-goo Lee, Taeuk Kim
| Challenge: | Large language models (LLMs) are not specifically trained to deal with ambiguous utterances . ambiguity can lead to varying interpretations of the same input based on different assumptions or background knowledge . |
| Approach: | They propose a pipeline that aligns large language models to manage ambiguous queries . they propose to use their own assessment of perceived ambiguity to detect and manage queries a . |
| Outcome: | Experimental results show that APA empowers LLMs to detect and manage ambiguous queries while retaining the ability to answer clear questions. |
Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents (2025.emnlp-main)
Copied to clipboard
| Challenge: | Current efforts to bridge the two modes of interaction are reactive, focusing on responding to user inputs rather than coordinating dialogue flows. |
| Approach: | They propose a dataset designed for transition-aware dialogue modeling that incorporates structurally diverse and integrated mode flows. |
| Outcome: | The proposed dataset outperforms baseline models in intent detection and mode transition handling. |
A Cross-Sentence Latent Variable Model for Semi-Supervised Text Sequence Matching (P19-1)
Copied to clipboard
| Challenge: | Existing approaches to text matching consider each sequence separately . a proposed model uses both sequences to generate a given relationship with a source sequence . |
| Approach: | They propose a latent variable model for predicting the relationship between a pair of text sequences by generating a sequence that has a given relationship with a source sequence. |
| Outcome: | The proposed model achieves state-of-the-art on natural language inference and paraphrase identification. |
Revisiting the Impact of Pursuing Modularity for Code Generation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study examines the impact of modularity on code generation in large language models . modularity is not a core factor for improving performance of code generation models, argues a new study . |
| Approach: | They introduce a new metric to measure the impact of modularity in code generation . they find modularity is not a core factor for improving performance of LLMs . |
| Outcome: | The proposed metric shows that modularity is not a core factor for improving performance . coding assistants are becoming increasingly essential for programmers . |
ENGinius: A Bilingual LLM Optimized for Plant Construction Engineering (2025.acl-industry)
Copied to clipboard
| Challenge: | Recent advances in large language models have drawn attention for their potential to automate and optimize processes across diverse sectors. |
| Approach: | They propose a specialized LLM for plant construction engineering that delivers optimized responses to plant engineers by leveraging enriched domain knowledge. |
| Outcome: | The proposed model delivers optimized responses to plant engineers by leveraging enriched domain knowledge. |
MAGIC: A Multi-Hop and Graph-Based Benchmark for Inter-Context Conflicts in Retrieval-Augmented Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing benchmarks for investigating knowledge conflict have notable limitations, including a narrow focus on the question answering setup, heavy reliance on entity substitution techniques, and a restricted range of conflict types. |
| Approach: | They propose a knowledge graph-based framework that generates varied and subtle conflicts between two similar yet distinct contexts while ensuring interpretability through the explicit relational structure of KGs. |
| Outcome: | The proposed framework generates varied and subtle conflicts between two similar yet distinct contexts while ensuring interpretability through the explicit relational structure of KGs. |
FCMR: Robust Evaluation of Financial Cross-Modal Multi-Hop Reasoning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks for multimodal large language models lack data contamination and complex queries . financial cross-modal multi-hop reasoning is difficult to evaluate and requires precise cross-module reasoning . |
| Approach: | They propose a benchmark to analyze the reasoning capabilities of multimodal large language models. |
| Outcome: | The proposed model is categorized into three difficulty levels—easy, medium, and hard—for step-by-step evaluation. |
Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations (2022.emnlp-main)
Copied to clipboard
Kang Min Yoo, Junyeob Kim, Hyuhng Joon Kim, Hyunsoo Cho, Hwiyeol Jo, Sang-Woo Lee, Sang-goo Lee, Taeuk Kim
| Challenge: | Intuitively, ground-truth labels should have as much impact in in-context learning as supervised learning, but the impact of the quality of demonstrations remains elusive. |
| Approach: | They propose to measure input-label correspondence and ground-truth label effect ratio . they propose to use verbosity of prompt templates and language model size as controlling factors . |
| Outcome: | The proposed metrics show that ground-truth labels have less impact than previously thought . the authors identify key components as controlling factors to achieve noise-resilient ICL . |
Think Just Enough: Leveraging Self-Assessed Confidence for Adaptive Reasoning in Language Models (2026.findings-eacl)
Copied to clipboard
| Challenge: | Recent advances in large reasoning models (LLMs) have shown remarkable capabilities in complex tasks such as mathematical problem solving and code generation. |
| Approach: | They propose a method for optimizing reasoning length via self-assessed confidence. |
| Outcome: | The proposed method improves computational efficiency without compromising answer quality. |
Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Out-of-distribution (OOD) detection aims to discern outliers from the intended data distribution, which is crucial to maintaining high reliability and a good user experience. |
| Approach: | They propose a framework that encourages intermediate features to learn layer-specialized representations and assembles them implicitly into a single representation to absorb rich information in the pre-trained language model. |
| Outcome: | The proposed framework is significantly more effective than previous studies in intent classification and OOD datasets. |
Hyper-CL: Conditioning Sentence Representations with Hypernetworks (2024.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to sentence embeddings do not capture fine-grained semantics of sentences. |
| Approach: | They propose a method that integrates hypernetworks with contrastive learning to generate conditioned sentence representations. |
| Outcome: | The proposed method narrows the performance gap with the bi-encoder architecture while maintaining the time efficiency characteristic of the tri-encoding approach. |
Summary Level Training of Sentence Rewriting for Abstractive Summarization (D19-54)
Copied to clipboard
| Challenge: | Existing models rely on sentence-level rewards or suboptimal labels to achieve summary-level ROUGE scores. |
| Approach: | They propose a model that extracts salient sentences from a document and paraphrases them to generate a summary. |
| Outcome: | The proposed model improves on CNN/Daily Mail and New York Times datasets. |
BlendX: Complex Multi-Intent Detection with Blended Patterns (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing datasets such as MixATIS and MixSNIPS have limitations in their formulation. |
| Approach: | They propose a set of multi-intent detection datasets that feature more diverse patterns than their predecessors. |
| Outcome: | The proposed datasets feature more diverse patterns than their predecessors and are more complex and diverse than existing datasets. |
Analysis of Multi-Source Language Training in Cross-Lingual Transfer (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies on cross-lingual transfer (XLT) methods address data scarcity problem . cross-linguistic transfer (xLT) techniques are effective at fine-tuning multilingual LMs . |
| Approach: | They propose to use multiple source languages to improve XLT by fine-tuning multilingual models . they propose to employ arbitrary combinations of source languages for XL to improve performance . |
| Outcome: | The proposed technique improves performance on language-agnostic or task-specific features by using multiple source languages. |
Self-Guided Contrastive Learning for BERT Sentence Representations (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods to derive sentence embeddings from pre-trained Transformers are unclear . a self-guided training method is used to fine-tune BERT in a supervised fashion . |
| Approach: | They propose a contrastive learning method that utilizes self-guidance to improve BERT sentence representations. |
| Outcome: | The proposed method is more effective than baselines on diverse sentence-related tasks and robust to domain shifts. |
Superficial Success vs. Internal Breakdown: An Empirical Study of Generalization in Adaptive Multi-Agent Systems (2026.findings-acl)
Copied to clipboard
| Challenge: | Adaptive multi-agent systems (MAS) are increasingly adopted as solutions to complex problems. |
| Approach: | They conduct extensive empirical study on adaptive multi-agent systems . they find they are prone to topological overfitting and exhibit illusory coordination . authors urge prioritization of generalization in MAS development and evaluation . |
| Outcome: | a new study shows adaptive multi-agent systems are prone to overfitting and lack coordination . the findings highlight the need to prioritize generalization in MAS development . |
Don’t Just Scratch the Surface: Enhancing Word Representations for Korean with Hanja (D19-1)
Copied to clipboard
| Challenge: | Existing knowledge of Korean and Chinese is based on cultural and historical reasons. |
| Approach: | They propose a method for improving Korean word representations using additional linguistic annotation by leveraging the fact that Hanja is closely related to Chinese. |
| Outcome: | The proposed approach improves representations on a novel Korean news headline generation task. |
Hybrid-Vector Retrieval for Visually Rich Documents: Combining Single-Vector Efficiency and Multi-Vector Accuracy (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to document retrieval are coarse and efficient, but expensive. |
| Approach: | a plug-and-play two-stage hybrid-vector framework is proposed to retrieve visually rich documents . HEAVEN efficiently retrieves candidate pages using a single-vektor method over VS-Pages . it also reranks candidates with a multi-vecctor method while filtering query tokens by linguistic importance . |
| Outcome: | HEAVEN achieves 99.87% of the Recall@1 performance of multi-vector models on average . it reduces per-query computation by 99.8%, achieving efficiency and accuracy . |
X-SNS: Cross-Lingual Transfer Prediction through Sub-Network Similarity (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Cross-lingual transfer (XLT) is an emergent ability of multilingual language models that preserves their performance when evaluated in non-English languages. |
| Approach: | They propose to use sub-network similarity between two languages as a proxy for XLT prediction. |
| Outcome: | The proposed method shows proficiency in ranking candidates for zero-shot XLT, achieving an improvement of 4.6% on average in terms of NDCG@3. |
Revisiting the Practical Effectiveness of Constituency Parse Extraction from Pre-trained Language Models (2022.coling-1)
Copied to clipboard
| Challenge: | Constituency Parse Extraction from Pre-trained Language Models (CPE-PLM) is a new paradigm that attempts to induce constituency parse trees based on the internal knowledge of pre-tried language models. |
| Approach: | They propose to use constituency parse trees from pre-trained language models to induce constituency trees by introducing a set of heterogeneous PLMs combined using two advanced ensemble methods. |
| Outcome: | The proposed approach is more effective than typical supervised parsers in few-shot settings. |
Universal Domain Adaptation for Robust Handling of Distributional Shifts in NLP (2023.findings-emnlp)
Copied to clipboard
Hyuhng Kim, Hyunsoo Cho, Sang-Woo Lee, Junyeob Kim, Choonghyun Park, Sang-goo Lee, Kang Yoo, Taeuk Kim
| Challenge: | Despite advances in computer vision, its application on language input still needs to be explored despite its feasibility. |
| Approach: | They propose a universal domain adaptation (uniDA) benchmark for natural language that offers thorough viewpoints of the model’s generalizability and robustness. |
| Outcome: | The proposed model can handle spoken language in the real world while also detecting unprocessable inputs from the target domain. |
ADVICE: Answer-Dependent Verbalized Confidence Estimation (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have enabled them to communicate their confidence in natural language, improving transparency and reliability. |
| Approach: | They propose a framework that promotes answer-grounded confidence estimation and analyze the dynamics of verbalized confidence estimation. |
| Outcome: | The proposed framework significantly improves confidence calibration while exhibiting strong generalization to unseen settings without degrading task performance. |
Does Localization Inform Unlearning? A Rigorous Examination of Local Parameter Attribution for Knowledge Unlearning in Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies emphasize localized unlearning, restricting parameter updates to specific regions to remove unrelated general knowledge. |
| Approach: | They revisit existing localized unlearning approaches and conduct experiments to evaluate their effectiveness. |
| Outcome: | The proposed method can remove unrelated knowledge without retraining . the proposed method is not robust enough to evaluate the trade-off between the competing goals of unlearning. |