Image de couverture de livre

Error as a Lens: Probing LLM Reasoning through Synthetic Misconception Generation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Xinming, Li, Jun
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Probing the "Psyche'' of Large Reasoning Models: Understanding Through a Human Lens
par: Chen, Yuxiang, et autres
Publié: (2025)

Persona Prompting as a Lens on LLM Social Reasoning
par: Yang, Jing, et autres
Publié: (2026)

Safety Compliance: Rethinking LLM Safety Reasoning through the Lens of Compliance
par: Hu, Wenbin, et autres
Publié: (2025)

LLM-based Cognitive Models of Students with Misconceptions
par: Sonkar, Shashank, et autres
Publié: (2024)

Oops, Wait: Token-Level Signals as a Lens into LLM Reasoning
par: Hwang, Jaehui, et autres
Publié: (2026)

LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokens
par: Zebaze, Armel, et autres
Publié: (2025)

LLM Bias Detection and Mitigation through the Lens of Desired Distributions
par: Shrestha, Ingroj, et autres
Publié: (2025)

MalruleLib: Large-Scale Executable Misconception Reasoning with Step Traces for Modeling Student Thinking in Mathematics
par: Chen, Xinghe, et autres
Publié: (2026)

Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators
par: Do, Heejin, et autres
Publié: (2026)

Reasoning Trajectories for Socratic Debugging of Student Code: From Misconceptions to Contradictions and Updated Beliefs
par: Al-Hossami, Erfan, et autres
Publié: (2025)

Rethinking LLM Memorization through the Lens of Adversarial Compression
par: Schwarzschild, Avi, et autres
Publié: (2024)

Enhancing Long-Chain Reasoning Distillation through Error-Aware Self-Reflection
par: Wu, Zhuoyang, et autres
Publié: (2025)

ChatLang-8: An LLM-Based Synthetic Data Generation Framework for Grammatical Error Correction
par: Park, Jeiyoon, et autres
Publié: (2024)

Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?
par: Zhou, Jingyan, et autres
Publié: (2023)

CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning
par: Zhu, Xinyu, et autres
Publié: (2026)

Generating Logically Consistent Synthetic Supply Chain Data with LLM-Driven Knowledge Graph Reasoning
par: Long, Yunbo, et autres
Publié: (2026)

Misconception Diagnosis From Student-Tutor Dialogue: Generate, Retrieve, Rerank
par: Mitton, Joshua, et autres
Publié: (2026)

Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning
par: Zhang, Dongxu, et autres
Publié: (2025)

LLM-based Generative Error Correction for Rare Words with Synthetic Data and Phonetic Context
par: Yamashita, Natsuo, et autres
Publié: (2025)

Learning from the Irrecoverable: Error-Localized Policy Optimization for Tool-Integrated LLM Reasoning
par: Liang, Qiao, et autres
Publié: (2026)

Temporal Consistency for LLM Reasoning Process Error Identification
par: Guo, Jiacheng, et autres
Publié: (2025)

CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs
par: Li, Li, et autres
Publié: (2025)

ICPC-Eval: Probing the Frontiers of LLM Reasoning with Competitive Programming Contests
par: Xu, Shiyi, et autres
Publié: (2025)

Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking
par: Feng, Jun, et autres
Publié: (2026)

Learning Wisdom from Errors: Promoting LLM's Continual Relation Learning through Exploiting Error Cases
par: Yin, Shaozhe, et autres
Publié: (2025)

Explanation Regularisation through the Lens of Attributions
par: Ferreira, Pedro, et autres
Publié: (2024)

Déjà Vu: Multilingual LLM Evaluation through the Lens of Machine Translation Evaluation
par: Kreutzer, Julia, et autres
Publié: (2025)

Towards the Development of Balanced Synthetic Data for Correcting Grammatical Errors in Arabic: An Approach Based on Error Tagging Model and Synthetic Data Generating Model
par: Alrehili, Ahlam, et autres
Publié: (2025)

Synthetic Data Generation for Training Diversified Commonsense Reasoning Models
par: Zhang, Tianhui, et autres
Publié: (2026)

Synthetic Dialogue Dataset Generation using LLM Agents
par: Abdullin, Yelaman, et autres
Publié: (2024)

Knowledge-Infused Legal Wisdom: Navigating LLM Consultation through the Lens of Diagnostics and Positive-Unlabeled Reinforcement Learning
par: Wu, Yang, et autres
Publié: (2024)

PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations
par: Wu, Yuhe, et autres
Publié: (2026)

Probing How Scalable Table Data Enhances General Long-Context Reasoning
par: Xie, Huaibing, et autres
Publié: (2026)

Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning
par: Yu, Erxin, et autres
Publié: (2025)

Inner-Probe: Discovering Copyright-related Data Generation in LLM Architecture
par: Ma, Qichao, et autres
Publié: (2024)

ThoughtProbe: Classifier-Guided Thought Space Exploration Leveraging LLM Intrinsic Reasoning
par: Wang, Zijian, et autres
Publié: (2025)

OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment
par: Liu, Tianci, et autres
Publié: (2025)

Decoding Alignment: A Critical Survey of LLM Development Initiatives through Value-setting and Data-centric Lens
par: Chalkidis, Ilias
Publié: (2025)

MEDSAGE: Enhancing Robustness of Medical Dialogue Summarization to ASR Errors with LLM-generated Synthetic Dialogues
par: Binici, Kuluhan, et autres
Publié: (2024)

Arithmetic Reasoning with LLM: Prolog Generation & Permutation
par: Yang, Xiaocheng, et autres
Publié: (2024)