Papers by Jaeyoung Kim

15 papers
Query-focused Referentiability Learning for Zero-shot Retrieval (2025.naacl-long)

Copied to clipboard

Challenge: Existing dense representations have shown limitations in zero-shot scenarios . however, passage representations fail to align with their gold queries .
Approach: They propose a query-focused concept of 'referentiable' which ensures passage representations are referenced by their gold queries.
Outcome: The proposed model outperforms existing models on the BEIR benchmark.
Aligning Large Language Models via Fine-grained Supervision (2024.acl-short)

Copied to clipboard

Challenge: Pre-trained large-scale language models often generate biased or toxic text, misaligning with human intentions.
Approach: They propose to use human feedback to improve LLM alignment by fine-grained token supervision . they ask annotators to edit less preferred responses to make them more favorable .
Outcome: The proposed method improves LLM alignment by up to 5.1% in terms of win rate compared with the traditional model.
Exploring the Impact of Corpus Diversity on Financial Pretrained Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing financial PLMs are not pretrained on sufficiently diverse financial data, leading to subpar generalization performance.
Approach: They propose to pretrain financial PLMs on financial corpus and train financial models on financial data.
Outcome: The proposed financial language models outperform existing financial PLMs on financial tasks even for unseen corpus groups.
D3: Dynamic Docid Decoding for Multi-Intent Generative Retrieval (2026.eacl-industry)

Copied to clipboard

Challenge: Existing GR systems rely on offline DocID assignment and constrained decoding . offline Doc ID assignment and decoding often prevents GR from capturing query-specific intent .
Approach: They propose a mechanism that adaptively refines DocIDs through query-informed identifier expansion.
Outcome: The proposed mechanism improves retrieval accuracy on unseen and multi-intent documents.
ESG-Kor: A Korean Dataset for ESG-related Information Extraction and Practical Use Cases (2024.findings-emnlp)

Copied to clipboard

Challenge: Pre-trained language models are exhibiting astonishing performances in various natural language processing tasks, including classification, question answering, machine translation, summarization, and conversation generation.
Approach: They built a Korean dataset to automatically extract Environmental, Social, and Governance (ESG) information from Korean companies’ sustainability reports and manually labeled it according to objective rules provided by ESG evaluation agencies.
Outcome: The proposed dataset extracts environmental, social, and governance information from Korean companies’ sustainability reports and labels it according to objective rules provided by ESG evaluation agencies.
Hierarchical Retrieval with Evidence Curation for Open-Domain Financial Question Answering on Standardized Documents (2025.findings-acl)

Copied to clipboard

Challenge: standardized documents share similar formats and table structures . this similarity forces traditional RAG methods to misidentify near-duplicate text .
Approach: They propose a hierarchical retrieval framework that performs hierarchically to reduce confusion among similar texts.
Outcome: The proposed framework reduces confusion among similar documents by removing irrelevant passages . it generates complementary queries to collect missing information .
Hierarchical Graph Convolutional Network Approach for Detecting Low-Quality Documents (2024.lrec-main)

Copied to clipboard

Challenge: Consistency within a document is a crucial feature indicative of its quality . low-quality documents often lack internal consistency or contain content unrelated to headlines .
Approach: They propose a hierarchical graph convolutional network that detects internal inconsistencies within a document and incongruences between the title and body.
Outcome: The proposed model outperforms existing models on the inconsistency dataset and on the publicly available incongruent-related dataset.
HIL: Hybrid Isotropy Learning for Zero-shot Performance in Dense retrieval (2024.naacl-long)

Copied to clipboard

Challenge: Recent advances in dense retrieval models have brought ColBERT to prominence in information retrieval, but it is underperforming in zero-shot tasks.
Approach: They propose a Hybrid Isotropy Learning architecture that integrates isotropic and anisotropic representations to improve zero-shot retrieval performance.
Outcome: The proposed model outperforms the baseline ColBERT model in BEIR benchmarks.
Relevance to Utility: Process-Supervised Rewrite for RAG (2026.findings-acl)

Copied to clipboard

Challenge: Existing bridge modules attempt to rewrite documents for better generation, but fail to capture "document utility".
Approach: They propose to observe reasoning process as process supervision and scale this observation to enhance reliability in distillation.
Outcome: The proposed method improves over strong bridging baselines on multiple open-domain question-answering benchmarks.
Bag of Tricks for In-Distribution Calibration of Pretrained Transformers (2023.findings-eacl)

Copied to clipboard

Challenge: Recent studies show that pre-trained language models (PLMs) often predict over-confidently.
Approach: They propose to use ensemble learning and data augmentation to improve confidence calibration for PLMs by combining calibration techniques with a trade-off between accuracy and classification.
Outcome: The proposed calibration method improves classification accuracy and confidence in pre-trained language models by combining several calibration techniques.
Investigating Counterfactual Unfairness in LLMs towards Identities through Humor (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) absorb social and cultural biases embedded in vast web-scale corpora and are increasingly deployed in high-stakes domains such as hiring, education, and law.
Approach: They propose a framework to investigate counterfactual unfairness through humor by observing how the model’s responses change when we swap who speaks and who is addressed while holding other factors constant.
Outcome: The proposed framework covers humor generation refusal, speaker intention inference, and relational/societal impact prediction tasks.
PyOpenDial: A Python-based Domain-Independent Toolkit for Developing Spoken Dialogue Systems with Probabilistic Rules (D19-3)

Copied to clipboard

Challenge: a recent development of spoken dialogue systems has enabled deep learning to achieve state-of-the-art performance.
Approach: They propose a Python-based domain-independent, open-source toolkit for spoken dialogue systems.
Outcome: The proposed toolkit extends OpenDial's Java-based architecture and provides new functions for neural dialogue state tracking and action planning.
From Curiosity to Clarity : Exploring the Impact of Consecutive Why-Questions (2025.findings-naacl)

Copied to clipboard

Challenge: a recent study has demonstrated the utility of consecutive why-questions in everyday life.
Approach: They used a WHY-Chain dataset to construct a model that asked a why-questions question . they also used objectives that capture the 'consecutive' characteristic of the data .
Outcome: The proposed model performed better on downstream tasks that require commonsense reasoning . the model was validated by ablation studies and the validity check .
Pseudo Outlier Exposure for Out-of-Distribution Detection using Pretrained Transformers (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods to detect out-of-distribution (OOD) samples are overconfident for real-world language applications.
Approach: They propose a method that constructs a surrogate OOD dataset by sequentially masking tokens related to ID classes.
Outcome: The proposed method can train a rejection network with ID and diverse outlier samples but requires additional data collection overhead.
Adaptive Retrieval for Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Existing reasoning-based rerankers suffer from bounded recall.
Approach: They propose a framework that leverages adaptive retrieval to ensure sufficient "bridge" documents are retrieved for reasoning-intensive retrieval.
Outcome: The proposed method outperforms baselines on reasoning-intensive retrieval tasks by 5.6%pt.

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