Pith. sign in

REVIEW 12 cited by

Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2308.03188 v2 pith:JWSPTDHB submitted 2023-08-06 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords arrayfeedbackincludingitselflanguagelargemodelspromising
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) have demonstrated remarkable performance across a wide array of NLP tasks. However, their efficacy is undermined by undesired and inconsistent behaviors, including hallucination, unfaithful reasoning, and toxic content. A promising approach to rectify these flaws is self-correction, where the LLM itself is prompted or guided to fix problems in its own output. Techniques leveraging automated feedback -- either produced by the LLM itself or some external system -- are of particular interest as they are a promising way to make LLM-based solutions more practical and deployable with minimal human feedback. This paper presents a comprehensive review of this emerging class of techniques. We analyze and taxonomize a wide array of recent work utilizing these strategies, including training-time, generation-time, and post-hoc correction. We also summarize the major applications of this strategy and conclude by discussing future directions and challenges.

Discussion (0). Sign in to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 24 citations worldwide. Full citation record

  1. FVRuleLearner: Operator-Level Reasoning Tree (Op-Tree)-Based Rules Learning for Formal Verification

    cs.AR 2026-03 unverdicted novelty 7.0 of 10

    FVRuleLearner retrieves learned operator-level reasoning rules to boost the functional correctness of LLM-generated SystemVerilog assertions by roughly 30 percentage points over simple prompting baselines.

  2. CogEEGAgent: Toward Autonomous Cognitive EEG Analysis with Grounded Execution and Selection-Aware Verification

    cs.AI 2026-07 conditional novelty 6.0 of 10

    An MNE-grounded EEG agent separates LLM semantic routing from deterministic commitment, participant-disjoint confirmation, and evidence-bound release, outperforming a matched lexical router and blocking adaptive-searc...

  3. LEACL: LLM-Enhanced Automatic Curriculum Learning for Reinforcement Learning in Long-Horizon Manipulation Tasks

    cs.RO 2026-07 conditional novelty 6.0 of 10

    LLMs generate subtask decompositions and ACL task spaces so sparse-reward RL solves long-horizon manipulation better than dense human rewards on five LIBERO tasks.

  4. ST-Veto: Spatio-Temporal Token Veto for Diffusion MLLMs via Taylor Prediction and Visual Grounding

    cs.AI 2026-07 conditional novelty 6.0 of 10

    ST-Veto improves reasoning in diffusion MLLMs by vetoing temporally unstable tokens and tokens with weak image grounding, swapping in safer near-boundary candidates.

  5. Multi-Turn On-Policy Distillation with Prefix Replay

    cs.LG 2026-07 conditional novelty 6.0 of 10

    ReOPD offline-distills multi-turn agentic LLMs via teacher-prefix replay plus step-decay sampling, matching online OPD accuracy at ≥4× speed with zero tool calls.

  6. SGIC: A Self-Guided Iterative Calibration Framework for RAG

    cs.CL 2025-06 conditional novelty 6.0 of 10

    SGIC feeds a model's own uncertainty scores back into its prompt for several calibration rounds and improves RAG accuracy on HotpotQA, NQ, and GSM8K.

  7. Direct Behavior Optimization: Unlocking the Potential of Lightweight LLMs

    cs.CL 2025-06 conditional novelty 6.0 of 10

    A gradient-free Monte Carlo tree search over JSON key-step plans produces few-shot demonstrations that let LLaMA3-8B and LLaMA3.2-3B outperform GPT-3.5 on most of seven BIG-Bench Hard tasks.

  8. Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning

    cs.CL 2025-08 reject novelty 5.0 of 10

    ASCoT claims later reasoning errors are more harmful than early ones and uses a position-weighted verifier to prune and correct CoT steps, but its key evidence is internally inconsistent.

  9. I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking

    cs.CV 2025-08 conditional novelty 5.0 of 10

    A text-first, multi-round visual feedback framework reports state-of-the-art top-1 accuracy on WikiMEL, WikiDiverse, and RichMEL.

  10. Enterprise Large Language Model Evaluation Benchmark

    cs.AI 2025-06 reject novelty 5.0 of 10

    A 14-task enterprise LLM benchmark built mostly from GPT-4o-generated labels and scored by GPT-4o-as-judge shows open-source models closing the reasoning gap, but the dataset is not public and the evaluation is partly...

  11. From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI

    cs.AI 2026-06 conditional novelty 4.0 of 10

    Autonomous AI becomes dependable when tool use is embedded in persistent workspaces with reusable skills, shifting evaluation from answers to task closure.

  12. Smoothie-Qwen: Post-Hoc Smoothing to Reduce Language Bias in Multilingual LLMs

    cs.CL 2025-07 conditional novelty 3.0 of 10

    Smoothie-Qwen reduces Chinese-language output in Qwen2.5-Coder by scaling down lm head weights of Chinese tokens, reaching 95% suppression on a synthetic elicitation set while keeping Korean MMLU accuracy roughly stable.

Pith tools