Imagen de Portada

Lost in the Noise: How Reasoning Models Fail with Contextual Distractors

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lee, Seongyun, Jo, Yongrae, Seo, Minju, Lee, Moontae, Seo, Minjoon
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think
por: Lee, Seongyun, et al.
Publicado: (2025)

Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language Models
por: Kim, Jiyeon, et al.
Publicado: (2026)

LG AI Research & KAIST at EHRSQL 2024: Self-Training Large Language Models with Pseudo-Labeled Unanswerable Questions for a Reliable Text-to-SQL System on EHRs
por: Jo, Yongrae, et al.
Publicado: (2024)

Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision
por: Lee, Seongyun, et al.
Publicado: (2023)

FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets
por: Ye, Seonghyeon, et al.
Publicado: (2023)

Rethinking the Role of Proxy Rewards in Language Model Alignment
por: Kim, Sungdong, et al.
Publicado: (2024)

How Well Do Large Language Models Truly Ground?
por: Lee, Hyunji, et al.
Publicado: (2023)

Differential Information Distribution: A Bayesian Perspective on Direct Preference Optimization
por: Won, Yunjae, et al.
Publicado: (2025)

Hierarchical Deconstruction of LLM Reasoning: A Graph-Based Framework for Analyzing Knowledge Utilization
por: Ko, Miyoung, et al.
Publicado: (2024)

Aligning to Thousands of Preferences via System Message Generalization
por: Lee, Seongyun, et al.
Publicado: (2024)

Shifting from Ranking to Set Selection for Retrieval Augmented Generation
por: Lee, Dahyun, et al.
Publicado: (2025)

Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
por: Seo, Minju, et al.
Publicado: (2025)

Leveraging Large Language Models for Active Merchant Non-player Characters
por: Kim, Byungjun, et al.
Publicado: (2024)

Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation
por: Lee, Seongyun, et al.
Publicado: (2024)

GRACE: Discriminator-Guided Chain-of-Thought Reasoning
por: Khalifa, Muhammad, et al.
Publicado: (2023)

Generating Plausible Distractors for Multiple-Choice Questions via Student Choice Prediction
por: Lee, Yooseop, et al.
Publicado: (2025)

How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?
por: Lee, Seongyun, et al.
Publicado: (2024)

Reasoning Models Better Express Their Confidence
por: Yoon, Dongkeun, et al.
Publicado: (2025)

Aligning Large Language Models by On-Policy Self-Judgment
por: Lee, Sangkyu, et al.
Publicado: (2024)

Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition
por: Kim, Jiyeon, et al.
Publicado: (2024)

Latent Reasoning via Sentence Embedding Prediction
por: Hwang, Hyeonbin, et al.
Publicado: (2025)

Fine-Grained and Thematic Evaluation of LLMs in Social Deduction Game
por: Kim, Byungjun, et al.
Publicado: (2024)

Understanding the Effects of Distractors on Reasoning Vision-Language Models
por: Bae, Jiyun, et al.
Publicado: (2025)

Semiparametric Token-Sequence Co-Supervision
por: Lee, Hyunji, et al.
Publicado: (2024)

Rethinking Code Refinement: Learning to Judge Code Efficiency
por: Seo, Minju, et al.
Publicado: (2024)

Better by Comparison: Retrieval-Augmented Contrastive Reasoning for Automatic Prompt Optimization
por: Lee, Juhyeon, et al.
Publicado: (2025)

Generative Prompt Internalization
por: Shin, Haebin, et al.
Publicado: (2024)

Reinforcement Learning from Reflective Feedback (RLRF): Aligning and Improving LLMs via Fine-Grained Self-Reflection
por: Lee, Kyungjae, et al.
Publicado: (2024)

Confidence-guided Refinement Reasoning for Zero-shot Question Answering
por: Jang, Youwon, et al.
Publicado: (2025)

Retrieval-Augmented Data Augmentation for Low-Resource Domain Tasks
por: Seo, Minju, et al.
Publicado: (2024)

"Lost-in-the-Later": Framework for Quantifying Contextual Grounding in Large Language Models
por: Tao, Yufei, et al.
Publicado: (2025)

SimuHome: A Temporal- and Environment-Aware Benchmark for Smart Home LLM Agents
por: Seo, Gyuhyeon, et al.
Publicado: (2025)

Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History
por: Kim, Serin, et al.
Publicado: (2026)

Hybrid Deep Searcher: Scalable Parallel and Sequential Search Reasoning
por: Ko, Dayoon, et al.
Publicado: (2025)

EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records
por: Lee, Gyubok, et al.
Publicado: (2023)

Fakes of Varying Shades: How Warning Affects Human Perception and Engagement Regarding LLM Hallucinations
por: Nahar, Mahjabin, et al.
Publicado: (2024)

MARIC: Multi-Agent Reasoning for Image Classification
por: Seo, Wonduk, et al.
Publicado: (2025)

Finding Answers in Thought Matters: Revisiting Evaluation on Large Language Models with Reasoning
por: Jo, Hwiyeol, et al.
Publicado: (2025)

FunctionChat-Bench: Comprehensive Evaluation of Language Models' Generative Capabilities in Korean Tool-use Dialogs
por: Lee, Shinbok, et al.
Publicado: (2024)

Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpus
por: Lee, Seungpil, et al.
Publicado: (2024)