No article text was recorded for this version.
self-correction failure
Version 2 of 2892 papers1,300 conceptsfrozen 2026-10-04
Papers in this version
- Blog: On the Intersection of Self-Correction and Trust in Language Models
- Blog: Synthetic Error Injection Fails to Elicit Self-Correction In Language Models
- Blog: Large Language Models Cannot Self-Correct Reasoning Yet
- Blog: Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?
- Blog: Large Language Models Cannot Self-Correct Reasoning Yet
- Blog: Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs
- Blog: Small Language Models Need Strong Verifiers to Self-Correct Reasoning
- Blog: GPT-4 Doesn’t Know It’s Wrong: An Analysis of Iterative Prompting for Reasoning Problems
- Blog: LLMs cannot find reasoning errors, but can correct them!
- Blog: Double-Checker: Enhancing Reasoning of Slow-Thinking LLMs via Self-Critical Fine-Tuning
- Blog: Small Language Models Need Strong Verifiers to Self-Correct Reasoning
- Blog: Structure Enables Effective Self-Localization of Errors in LLMs
- Blog: Refining Critical Thinking in LLM Code Generation: A Faulty Premise-based Evaluation Framework
- Blog: RefineBench: Evaluating Refinement Capability of Language Models via Checklists
- Blog: Structure Enables Effective Self-Localization of Errors in LLMs
- Blog: Evaluating LLMs at Detecting Errors in LLM Responses
- Blog: Self-Convinced Prompting: Few-Shot Question Answering with Repeated Introspection
- Blog: ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection
- Blog: Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks
- Blog: RefineBench: Evaluating Refinement Capability in Language Models
- Blog: CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
- Blog: How Well Can Reasoning Models Identify and Recover from Unhelpful Thoughts?
- Blog: When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs
- Blog: Learning to Self-Correct through Chain-of-Thought Verification
- Blog: FB-Bench: A Fine-Grained Multi-Task Benchmark for Evaluating LLMs' Responsiveness to Human Feedback
- Blog: RefineBench: Evaluating Refinement Capability of Language Models via Checklists
- Blog: Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction
- Blog: On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks
- Blog: T-Eval: Evaluating the Tool Utilization Capability Step by Step
- Blog: VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoning
- Blog: Connecting Giants: Synergistic Knowledge Transfer of Large Multimodal Models for Few-Shot Learning
- Blog: Understanding the Dark Side of LLMs' Intrinsic Self-Correction
- Blog: Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs
- Blog: SELF-REDRAFT: Eliciting Intrinsic Exploration-Exploitation Balance in Test-Time Scaling for Code Generation
- Blog: Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs
- Blog: Have LLMs Advanced Enough? A Challenging Problem Solving Benchmark For Large Language Models
- Blog: Towards Scalable Automated Alignment of LLMs: A Survey
- Blog: GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements
- Blog: Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction
- Blog: CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs' Mathematical Reasoning Capabilities
- Blog: EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity
- Blog: Hallucination is Inevitable: An Innate Limitation of Large Language Models
- Blog: CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
- Blog: Unleashing the Potential of Large Language Models as Prompt Optimizers: An Analogical Analysis with Gradient-based Model Optimizers
- Blog: Reasoning in Token Economies: Budget-Aware Evaluation of LLM Reasoning Strategies
- Blog: A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning
- Blog: Self-Correcting Code Generation Using Small Language Models
- Blog: Illusions of reflection: open-ended task reveals systematic failures in Large Language Models' reflective reasoning
- Blog: Error Reflection Prompting: Can Large Language Models Successfully Understand Errors?
- Blog: GeoBench: Rethinking Multimodal Geometric Problem-Solving via Hierarchical Evaluation
- Blog: Bag of Tricks for Inference-time Computation of LLM Reasoning
- Blog: Delusions of Large Language Models
- Blog: A Probabilistic Inference Scaling Theory for LLM Self-Correction
- Blog: Towards Reasoning in Large Language Models via Multi-Agent Peer Review Collaboration
- Blog: Recursive Chain-of-Feedback Prevents Performance Degradation from Redundant Prompting
- Blog: Improved LLM Agents for Financial Document Question Answering
- Blog: MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains
- Blog: Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers
- Blog: Evolving LLMs' Self-Refinement Capability via Synergistic Training-Inference Optimization
- Blog: Is Self-Repair a Silver Bullet for Code Generation?
Showing 60 of 892 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_self_correction_failure_b6f84981,
title = {self-correction failure},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/self-correction-failure/rdr_b6f84981b8604e7198a0ff9bd3129efc},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_self_correction_failure_b6f84981_v2,
title = {self-correction failure},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/self-correction-failure/rdr_b6f84981b8604e7198a0ff9bd3129efc/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}