SK
Seungone Kim
cs.CLcs.AIcs.LGcs.CVcs.CYcs.IRcs.MMcs.PLcs.SEeess.AS
On Valency
published · living versionsW_kwzn9zcn·v1 · currentpublished
Aligning Autoresearch: Co-Improvement between Agents and Humans
with Tianjian Li, Chuanyang Jin, Tong Chen, John Hoffman +8
1 version
W_t6demzc7·v1published
Preprints & journals
49 papers in the corpus · 2022–2026Into the Unknown: Benchmarking AI agents on open scientific research problems2610.19159v1 · Seungone Kim, Jiayi Geng, Young-Jun Lee et al.2026 · 0 citationsarXiv
ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research2610.02202v1 · Sohyeon Kim, Yoonho Lee, Bo Liu et al.2026 · 0 citationsarXiv
EurekaBench: Measuring Agentic Ability to Discover New Scientific Insights2610.00492v1 · Jiayi Geng, Zhengxuan Wu, Kevin S. Chen et al.2026 · 0 citationsarXiv
Efficient Test-Time Adaptation through Human-AI Interaction2609.04141v1 · Zora Zhiruo Wang, Apurva Gandhi, Rulin Shao et al.2026 · 0 citationsarXiv
SPADE: Self-Play in Adaptive Synthetic Executable Environments2608.19197v3 · Bo Liu, Simon Yu, Yiding Jiang et al.2026 · 0 citationsarXiv
LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL2607.04412v2 · Yujin Kim, Namgyu Ho, Sangmin Hwang et al.2026 · 0 citationsarXiv
Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks2606.29082v1 · Young-Jun Lee, Seungone Kim, Minki Kang et al.2026 · 0 citationsarXiv
K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts2606.02404v1 · Nahyun Lee, Dongkeun Yoon, Guijin Son et al.2026 · 0 citationsarXiv
Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization2605.26457v1 · Anmol Agarwal, Natalie Neamtu, Pranjal Aggarwal et al.2026 · 0 citationsarXiv
On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists2605.20668v1 · Seungone Kim, Dongkeun Yoon, Kiril Gashteovski et al.2026 · 1 citationarXiv
Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs2605.09063v4 · Guijin Son, Seungone Kim, Catherine Arnett et al.2026 · 0 citationsarXiv
Reasoning over mathematical objects: on-policy reward modeling and test time aggregation2603.18886v1 · Pranjal Aggarwal, Marjan Ghazvininejad, Seungone Kim et al.2026 · 0 citationsarXiv
SPICE: Self-Play In Corpus Environments Improves Reasoning2510.24684v1 · Bo Liu, Chuanyang Jin, Seungone Kim et al.2025 · 0 citationsarXiv
VideoJudge: Bootstrapping Enables Scalable Supervision of MLLM-as-a-Judge for Video Understanding2509.21451v1 · Abdul Waheed, Zhen Wu, Dareen Alharthi et al.2025 · 0 citationsarXiv
OptimalThinkingBench: Evaluating Over and Underthinking in LLMs2508.13141v2 · Pranjal Aggarwal, Seungone Kim, Jack Lanchantin et al.2025 · 1 citationarXiv
Datasheets Aren't Enough: DataRubrics for Automated Quality Metrics and Accountability2506.01789v2 · Genta Indra Winata, David Anugraha, Emmy Liu et al.2025 · 0 citationsarXiv
Latent Reasoning via Sentence Embedding Prediction2505.22202v2 · Hyeonbin Hwang, Byeongguk Jeon, Seungone Kim et al.2025 · 1 citationarXiv
Measuring Sycophancy of Language Models in Multi-turn Dialogues2505.23840v4 · Jiseung Hong, Grace Byun, Seungone Kim et al.2025 · 18 citationsFindings of the Association for Computational Linguistics: EMNLP 2025, pages 2239-2259
FREESON: Retriever-Free Retrieval-Augmented Reasoning via Corpus-Traversing MCTS2505.16409v1 · Chaeeun Kim, Seungone Kim2025 · 0 citationsarXiv
Web-Shepherd: Advancing PRMs for Reinforcing Web Agents2505.15277v2 · Hyungjoo Chae, Sunghwan Kim, Junhee Cho et al.2025 · 3 citationsarXiv
Reasoning Models Better Express Their Confidence2505.14489v2 · Dongkeun Yoon, Seungone Kim, Sohee Yang et al.2025 · 2 citationsarXiv
The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think2505.10185v1 · Seongyun Lee, Seungone Kim, Minju Seo et al.2025 · 0 citationsarXiv
M-Prometheus: A Suite of Open Multilingual LLM Judges2504.04953v2 · Jos'e Pombal, Dongkeun Yoon, Patrick Fernandes et al.2025 · 0 citationsarXiv
Scaling Evaluation-time Compute with Reasoning Models as Evaluators2503.19877v3 · Seungone Kim, Ian Wu, Jinu Lee et al.2025 · 0 citationsarXiv
Bridging the Data Provenance Gap Across Text, Speech and Video2412.17847v2 · Shayne Longpre, Nikhil Singh, Manuel Cherep et al.2024 · 4 citationsarXiv
LLM-as-an-Interviewer: Beyond Static Testing Through Dynamic LLM Evaluation2412.10424v3 · Eunsu Kim, Juyoung Suk, Seungone Kim et al.2024 · 4 citationsarXiv
Evaluating Language Models as Synthetic Data Generators2412.03679v2 · Seungone Kim, Juyoung Suk, Xiang Yue et al.2024 · 8 citationsarXiv
MM-Eval: A Multilingual Meta-Evaluation Benchmark for LLM-as-a-Judge and Reward Models2410.17578v2 · Guijin Son, Dongkeun Yoon, Juyoung Suk et al.2024 · 2 citationsarXiv
Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages2410.16153v3 · Xiang Yue, Yueqi Song, Akari Asai et al.2024 · 2 citationsarXiv
Better Instruction-Following Through Minimum Bayes Risk2410.02902v4 · Ian Wu, Patrick Fernandes, Amanda Bertsch et al.2024 · 1 citationarXiv
Can Language Models Evaluate Human Written Text? Case Study on Korean Student Writing for Education2407.17022v1 · Seungyoon Kim, Seungone Kim2024 · 0 citationsarXiv
Consent in Crisis: The Rapid Decline of the AI Data Commons2407.14933v2 · Shayne Longpre, Robert Mahari, Ariel Lee et al.2024 · 28 citationsarXiv
The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models2406.05761v2 · Seungone Kim, Juyoung Suk, Ji Yong Cho et al.2024 · 7 citationsarXiv
Aligning to Thousands of Preferences via System Message Generalization2405.17977v2 · Seongyun Lee, Sue Hyun Park, Seungone Kim et al.2024 · 5 citationsarXiv
Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models2405.01535v2 · Seungone Kim, Juyoung Suk, Shayne Longpre et al.2024 · 62 citationsarXiv
Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards2404.10346v4 · Hyeonbin Hwang, Doyoung Kim, Seungone Kim et al.2024 · 6 citationsarXiv
Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models2404.02575v1 · Hyungjoo Chae, Yeonghyeon Kim, Seungone Kim et al.2024 · 1 citationarXiv
KMMLU: Measuring Massive Multitask Language Understanding in Korean2402.11548v2 · Guijin Son, Hanwool Lee, Sungdong Kim et al.2024 · 10 citationsarXiv
Multi-Task Inference: Can Large Language Models Follow Multiple Instructions at Once?2402.11597v2 · Guijin Son, Sangwon Baek, Sangdae Nam et al.2024 · 6 citationsarXiv
LangBridge: Multilingual Reasoning Without Multilingual Supervision2401.10695v2 · Dongkeun Yoon, Joel Jang, Sungdong Kim et al.2024 · 7 citationsarXiv
Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation2401.06591v1 · Seongyun Lee, Seungone Kim, Sue Hyun Park et al.2024 · 16 citationsarXiv
Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging2310.11564v1 · Joel Jang, Seungone Kim, Bill Yuchen Lin et al.2023 · 6 citationsarXiv
Prometheus: Inducing Fine-grained Evaluation Capability in Language Models2310.08491v2 · Seungone Kim, Jamin Shin, Yejin Cho et al.2023 · 15 citationsarXiv
FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets2307.10928v4 · Seonghyeon Ye, Doyoung Kim, Sungdong Kim et al.2023 · 10 citationsarXiv
The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning2305.14045v2 · Seungone Kim, Se June Joo, Doyoung Kim et al.2023 · 53 citationsarXiv
CoTEVer: Chain of Thought Prompting Annotation Toolkit for Explanation Verification2303.03628v1 · Seungone Kim, Se June Joo, Yul Jang et al.2023 · 4 citationsarXiv
Exploring the Benefits of Training Expert Language Models over Instruction Tuning2302.03202v2 · Joel Jang, Seungone Kim, Seonghyeon Ye et al.2023 · 23 citationsarXiv
Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue Summarization2209.00930v1 · Seungone Kim, Se June Joo, Hyungjoo Chae et al.2022 · 17 citationsarXiv
Can Language Models perform Abductive Commonsense Reasoning?2207.05155v1 · Seungone Kim2022 · 0 citationsarXiv
Career total: 59 works. 49 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.