Pith. sign in

REVIEW 15 cited by

Generating Sequences by Learning to Self-Correct

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 2211.00053 v1 pith:3ZWTTWAR submitted 2022-10-31 cs.CL

Generating Sequences by Learning to Self-Correct

classification cs.CL
keywords languagebasecorrectorgenerationgeneratorimperfectconstraintscorrect
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Sequence generation applications require satisfying semantic constraints, such as ensuring that programs are correct, using certain keywords, or avoiding undesirable content. Language models, whether fine-tuned or prompted with few-shot demonstrations, frequently violate these constraints, and lack a mechanism to iteratively revise their outputs. Moreover, some powerful language models are of extreme scale or inaccessible, making it inefficient, if not infeasible, to update their parameters for task-specific adaptation. We present Self-Correction, an approach that decouples an imperfect base generator (an off-the-shelf language model or supervised sequence-to-sequence model) from a separate corrector that learns to iteratively correct imperfect generations. To train the corrector, we propose an online training procedure that can use either scalar or natural language feedback on intermediate imperfect generations. We show that Self-Correction improves upon the base generator in three diverse generation tasks - mathematical program synthesis, lexically-constrained generation, and toxicity control - even when the corrector is much smaller than the base generator.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 15 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination

    cs.LG 2026-06 unverdicted novelty 7.0

    DICE formalizes multi-agent LLM coordination as discounted incomplete-information Markov games and introduces Heterogeneous Quantal Response Equilibrium (HQRE) to achieve unique stable equilibria with bounded regret, ...

  2. Perturbation Dose Responses in Recursive LLM Loops: Raw Switching, Stochastic Floors, and Persistent Escape under Append, Replace, and Dialog Updates

    cs.AI 2026-05 unverdicted novelty 7.0

    In 30-step recursive LLM loops, append-mode persistent escape from source basins reaches 50% near 400 tokens under full history but plateaus below 50% under tail-clip memory policy, while replace-mode switching largel...

  3. Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction

    cs.CL 2026-04 unverdicted novelty 7.0

    VeriGUI adds a Thinking-Verification-Action-Expectation loop and two-stage training on synthetic failures to reduce undetected action errors and improve recovery in GUI automation.

  4. User-Assistant Bias in LLMs

    cs.CL 2025-08 unverdicted novelty 7.0

    LLMs show strong user bias in role-tagged contexts that is amplified by preference alignment and can be reduced or controlled through targeted fine-tuning and DPO.

  5. DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination

    cs.LG 2026-06 conditional novelty 6.5

    HQRE entropy regularization makes multi-agent LLM coordination well-posed, yielding unique equilibria, linear mirror convergence, bounded Bayesian regret, and DICE gains of 4.3–8.5 pp on reasoning/planning tasks.

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

    cs.LG 2026-07 conditional novelty 6.0

    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.

  7. DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization

    cs.LG 2026-05 unverdicted novelty 6.0

    DRIFT achieves multi-turn RL performance via offline importance-weighted SFT by leveraging the equivalence of KL-regularized RL to weighted supervised learning.

  8. STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning

    cs.LG 2026-05 unverdicted novelty 6.0

    STRIDE co-trains generator and verifier on outcome rewards alone to deliver learnable stepwise language feedback that redirects LLM reasoning trajectories and outperforms scalar-reward baselines.

  9. LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

    cs.SE 2024-03 unverdicted novelty 6.0

    LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.

  10. Reasoning with Language Model is Planning with World Model

    cs.CL 2023-05 unverdicted novelty 6.0

    RAP turns LLMs into dual world-model and planning agents via MCTS to generate better reasoning paths, outperforming CoT baselines and achieving 33% relative gains over GPT-4 CoT using LLaMA-33B on plan generation.

  11. Language Models can Solve Computer Tasks

    cs.CL 2023-03 accept novelty 6.0

    Pre-trained LLMs using recursive criticism and improvement prompting achieve state-of-the-art results on the MiniWoB++ computer task benchmark with only a handful of demonstrations and no task-specific reward function.

  12. EPPC-OASIS: Ontology-Aware Adaptation and Structured Inference Refinement for Electronic Patient-Provider Communication Mining in Secure Messages

    cs.AI 2026-05 unverdicted novelty 5.0

    EPPC-OASIS combines ontology-aware fine-tuning via Wasserstein alignment with structured inference refinement to extract EPPC codes from secure messages, reporting 77.13% Code+Sub-code F1 and 63.83% Triplet F1 with sm...

  13. Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding

    cs.LG 2026-04 unverdicted novelty 5.0

    A co-evolving proposer-critic RL framework improves GUI grounding accuracy by letting the model critique its own proposals rendered on screenshots.

  14. Self-Refine: Iterative Refinement with Self-Feedback

    cs.CL 2023-03 unverdicted novelty 5.0

    Self-Refine boosts LLM outputs by ~20% on average across seven tasks by having the same model iteratively generate, critique, and refine its own responses.

  15. DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes

    cs.AI 2026-05 unverdicted novelty 4.0

    DenoiseRL optimizes recovery from noisy prefixes in weak-model reasoning failures to improve performance and self-correction on math and general reasoning benchmarks without external supervision.