Compositional Multi-hop Factual Error Correction via Decomposition-and-Injection

• URL: http://arxiv.org/abs/2605.02277v1
• Date: Mon, 04 May 2026 07:08:39 GMT
• Title: Compositional Multi-hop Factual Error Correction via Decomposition-and-Injection
• Abstract summary: We present CECoR (Compositional Error Correction via Reasoning-aware Synthesis), a reasoning-aware framework for compositional error correction.<n> CECoR decomposes multi-hop claims into interpretable reasoning steps and injects controlled perturbations to synthesize high-quality training pairs.<n>A two-stage learning strategy combining supervised fine-tuning and reinforcement learning improves factual accuracy and robustness.
• Score: 60.34509125517578
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Factual Error Correction (FEC) aims to revise inaccurate text into statements that are factually consistent with external evidence. Although recent methods perform well on single-hop correction, they often treat claims as atomic units and struggle with multi-hop cases that require compositional reasoning across multiple evidence sources. This challenge is further amplified by limited paired data and difficulties in locating semantic errors within complex reasoning chains. We present CECoR (Compositional Error Correction via Reasoning-aware Synthesis), a reasoning-aware framework that introduces a Decomposition and Injection paradigm for compositional error correction. CECoR decomposes multi-hop claims into interpretable reasoning steps and injects controlled perturbations to synthesize high-quality training pairs. A two-stage learning strategy combining supervised fine-tuning and reinforcement learning improves factual accuracy and robustness. Comprehensive evaluations show that CECoR achieves strong performance on multi-hop benchmarks, outperforming both distantly supervised methods and few-shot LLM baselines. It also generalizes effectively to single-hop correction and remains stable under noisy evidence, demonstrating its versatility for real-world factual correction.

Related papers

• RePair: Turning Retrieval Failures into Counterfactual Hard Pairs [15.148342372814662]
  RePair mines false positives bidirectionally, applies LLM-guided counterfactual editing, and trains with a local hard-pair contrastive objective.<n>On Flickr30K and COCO30K, RePair outperforms controlled augmentation baselines with only 107K synthetic samples.
  arXiv  Detail & Related papers  (2026-08-30T06:47:38Z)
• Mask-to-Correct$^+$: Leveraging Retriever Diversity for Masking-guided Faithful Fact Correction [2.6365690297272617]
  The rapid spread of misinformation on social media highlights the need for robust, automated fact correction frameworks.<n>We propose a training-free, inference-only Retrieval Augmented Generation (RAG) based framework that leverages diversity-aware masking to identify erroneous claims.<n>We further introduce M$$C$+$, an ensemble-based framework that combines corrections across multiple rankers to reduce retrieval bias and improve robustness.
  arXiv  Detail & Related papers  (2026-04-21T14:13:07Z)
• Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration [49.9937230730202]
  We propose Search-R2, a novel Actor-Refiner collaboration framework that enhances reasoning through targeted intervention.<n>Our approach decomposes the generation process into an Actor, which produces initial reasoning trajectories.<n>We show that Search-R2 consistently outperforms strong RAG and RL-based baselines across model scales.
  arXiv  Detail & Related papers  (2026-02-03T15:32:09Z)
• CRAFT: Calibrated Reasoning with Answer-Faithful Traces via Reinforcement Learning for Multi-Hop Question Answering [19.391824811629125]
  Retrieval-augmented generation (RAG) is widely used to ground Large Language Models (LLMs) for multi-hop question answering.<n> Reasoning in multi-hop QA is inherently complex due to multi-hop composition and is further destabilized by noisy retrieval.<n>We propose CRAFT, a reinforcement learning framework that trains models to perform faithful reasoning during response generation.
  arXiv  Detail & Related papers  (2026-02-01T17:33:39Z)
• Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models [66.36240676392502]
  Chain-of-thought (CoT) reasoning has become the standard paradigm for enabling Large Language Models (LLMs) to solve complex problems.<n>Recent studies reveal a sharp performance drop in reasoning hop generalization scenarios.<n>We propose test-time correction of reasoning, a lightweight intervention method that dynamically identifies and deactivates ep heads in the reasoning process.
  arXiv  Detail & Related papers  (2026-01-29T03:24:32Z)
• Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning [53.25336975467293]
  We present the first theoretical error decomposition analysis of methods such as perplexity and self-consistency.<n>Our analysis reveals a fundamental trade-off: perplexity methods suffer from substantial model error due to the absence of a proper consistency function.<n>We propose Reasoning-Pruning Perplexity Consistency (RPC), which integrates perplexity with self-consistency, and Reasoning Pruning, which eliminates low-probability reasoning paths.
  arXiv  Detail & Related papers  (2025-02-01T18:09:49Z)
• Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification [52.095460362197336]
  Large language models (LLMs) struggle with consistent and accurate reasoning. LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors. We propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification.
  arXiv  Detail & Related papers  (2024-10-05T05:21:48Z)
• Cross-modal Active Complementary Learning with Self-refining Correspondence [54.61307946222386]
  We propose a Cross-modal Robust Complementary Learning framework (CRCL) to improve the robustness of existing methods. ACL exploits active and complementary learning losses to reduce the risk of providing erroneous supervision. SCC utilizes multiple self-refining processes with momentum correction to enlarge the receptive field for correcting correspondences.
  arXiv  Detail & Related papers  (2023-10-26T15:15:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.