Papers by Hyungjoo Chae

14 papers
One Missing Piece for Open-Source Reasoning Models: A Dataset to Mitigate Cold-Starting Short CoT LLMs in RL (2025.acl-industry)

Copied to clipboard

Challenge: Existing large reasoning models are limited by their closed nature and high API costs and safety issues.
Approach: They propose to build a long CoT dataset with existing short CoT LLMs that are not trained for inference-time scaling.
Outcome: The proposed model achieves quality comparable to—or slightly below—R1 and is able to think longer and provide control over the thought budget to better manage the overthinking problem.
Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-Shot Question Answering (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for enhancing QA performance of Large Language Models (LLMs) have limitations, including duplicated entities or relations, reduced evidence density, and failure to highlight crucial evidence.
Approach: They propose an Evidence-focused Fact Summarization framework for enhanced QA with knowledge-augmented Large Language Models (LLMs) that incorporates external knowledge into LLMs to improve QA performance.
Outcome: The proposed framework improves LLM’s zero-shot QA performance especially when noisy facts are retrieved.
Coffee-Gym: An Environment for Evaluating and Improving Natural Language Feedback on Erroneous Code (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have made great progress in code generation, however, they still produce errors.
Approach: They propose a RL environment that provides feedback on code editing by analyzing the performance of the revised code in unit tests.
Outcome: The proposed model outperforms baselines in enhancing open-source code LLMs’ code editing, making them comparable with closed-source LLM.
VerifiNER: Verification-augmented NER via Knowledge-grounded Reasoning with Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Recent approaches in domain-specific named entity recognition (NER) have shown remarkable advances, but they still lack faithfulness, producing erroneous predictions.
Approach: They propose a framework that revises errors from existing NER methods using knowledge to produce more faithful predictions.
Outcome: The proposed framework can validate errors from existing models as a model-agnostic approach.
CoTEVer: Chain of Thought Prompting Annotation Toolkit for Explanation Verification (2023.eacl-demo)

Copied to clipboard

Challenge: Chain-of-thought prompting generates an explanation before the final prediction, but its performance is affected by the factual accuracy of the explanation.
Approach: They propose a toolkit for annotating the factual correctness of generated explanations and collecting revision data of wrong explanations.
Outcome: The proposed toolkit is publicly available at https://github.com/SeungoneKim/CoTEVer.
Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents (2023.emnlp-main)

Copied to clipboard

Challenge: a human-like chatbot requires commonsense reasoning to comprehend and respond to information . however, identifying and aggregating key evidence within a single hop is a challenge . a knowledge distillation framework is proposed that leverages LLMs as unreliable teachers .
Approach: They propose a framework that leverages large language models as unreliable teachers to facilitate multi-hop reasoning over a dialogue context.
Outcome: The proposed framework leverages LLMs as unreliable teachers and selectively distills consistent and helpful rationales via alignment filters.
The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models (2025.naacl-long)

Copied to clipboard

Challenge: a recent study evaluated language models using abstract evaluation criteria that lack the flexibility and granularity of human assessment.
Approach: They propose a benchmark to evaluate nine distinct language models' capabilities . they use instance-specific evaluation criteria to mirror human evaluation .
Outcome: The proposed benchmark evaluates nine distinct capabilities of language models across 77 tasks.
Can You Share Your Story? Modeling Clients’ Metacognition and Openness for LLM Therapist Evaluation (2025.findings-acl)

Copied to clipboard

Challenge: Existing evaluation methods for psychological counseling rely on client simulators that clearly disclose internal states to the therapist, making it difficult to determine whether an LLM therapist can uncover unexpressed perspectives.
Approach: They propose a new evaluation framework featuring a controllable and realistic client simulator which dynamically adapts itself based on the ongoing counseling session.
Outcome: The proposed evaluation framework features a realistic and controllable client simulator which dynamically adapts itself based on the ongoing counseling session, offering a more realistic and challenging evaluation environment.
ToolHaystack: Stress-Testing Tool-Augmented Language Models in Realistic Long-Term Interactions (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing evaluations assume tool use in short contexts, offering limited insight into model behavior during realistic long-term interactions.
Approach: a benchmark is a tool to test long-term tool use in large language models . the tool includes multiple tasks execution contexts and realistic noise .
Outcome: a new benchmark tests the tool use capabilities in long-term interactions.
Towards Lifelong Dialogue Agents via Timeline-based Memory Management (2025.naacl-long)

Copied to clipboard

Challenge: Existing studies focus on getting rid of outdated memories to improve retrieval quality, but we argue that such memories provide rich, important contextual cues for response generation (RG).
Approach: They propose a framework for LLM-based lifelong dialogue agents that discards memory removal and manages large-scale memories by linking them based on their temporal and cause-effect relation.
Outcome: The proposed framework augments RG with memory timelines based on evolution or causality of relevant past events.
Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Prior work has used LLMs to generate programming language and applied external compilers for such tasks.
Approach: They propose a framework that expresses task-level logic with pseudocode and tailors it to each instance and simulates execution of it.
Outcome: The proposed framework outperforms baselines in diverse reasoning tasks.
Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics (2025.findings-naacl)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) have led to their adaptation as conversational agents.
Approach: They propose a new benchmark that uses 8K multi-choice questions to assess the personality of Large Language Models.
Outcome: The proposed personality test outperforms existing personality tests for LLMs in reliability and validity.
Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue Summarization (2022.coling-1)

Copied to clipboard

Challenge: Existing frameworks that use commonsense as supervision only use input knowledge, but it generates more informative and consistent summaries.
Approach: They propose to leverage the unique characteristics of dialogues sharing commonsense knowledge to solve the difficulties in summarizing them.
Outcome: The proposed framework generates more informative and consistent summaries with injected commonsense knowledge than existing methods.
Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization (2025.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for reward models show a weak correlation with performance of optimized policies . existing benchmarks do not accurately assess the true capabilities of reward models .
Approach: They explore how reward overoptimization captures how well a reward model aligns with human preferences and the dynamics of the learning signal it provides to the policy.
Outcome: The proposed benchmarks show that reward overoptimization is a weak factor . the high correlation with degree of overoptimalization leads to lower correlation with downstream performance .

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