Distill and Align Decomposition for Enhanced Claim Verification

Challenge:	Existing methods for complex claim verification struggle to align decomposition quality with verification performance.
Approach:	They propose a reinforcement learning approach that optimizes decomposition quality and verifier alignment using Group Relative Policy Optimization.
Outcome:	The proposed method outperforms prompt-based approaches and existing methods in six evaluation settings.

Similar Papers

Overview

Challenge

Approach

Outcome

Optimizing Decomposition for Optimal Claim Verification (2025.acl-long)

Copied to clipboard

Yining Lu, Noah Ziems, Hy Dang, Meng Jiang

Responsible & Trustworthy NLP

Challenge:	Existing decomposition and verification paradigms ignore their interactions and potential misalignment.
Approach:	They propose a reinforcement learning framework that leverages verifier feedback to learn a policy for dynamically decomposing claims to verifier-preferred atomicity.
Outcome:	The proposed framework outperforms existing decomposition policies in verification confidence tests . it improves accuracy and confidence by 0.12 on average across varying verifiers, datasets, and atomcities of input claims.

DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning (2026.findings-acl)

Copied to clipboard

Xiwen Chen, Wenhui Zhu, Peijie Qiu, Xuanzhao Dong, Hao Wang, Haiyu Wu, Huayu Li, Aris Sotiras, Yalin Wang, Abolfazl Razi

Reasoning

Challenge:	Existing methods for group-relative policy optimization rely on scalar correctness rewards that are often non-injective with respect to semantic content.
Approach:	They propose a framework that calibrates the reward signal using the semantic density of sampled groups.
Outcome:	The proposed framework outperforms strong baselines on five math benchmarks with 7,000 samples and 55 cost.

Veri-R1: Toward Precise and Faithful Claim Verification via Online Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Qi He, Cheng Qian, Xiusi Chen, Bingxiang He, Yi R. Fung, Heng Ji

Reasoning

Challenge:	Existing approaches to online claim verification rely on prompt engineering or pre-designed reasoning workflows.
Approach:	They propose an online reinforcement learning framework that enables an LLM to interact with a search engine and receive reward signals that explicitly shape its planning, retrieval, and reasoning behaviors.
Outcome:	Empirical results show that Veri-R1 improves joint accuracy by 30% and doubles evidence score, often surpassing larger-scale model counterparts.

Verifying the Subjective: Structured Multilingual Rewards for Low-Resource Alignment (2026.findings-acl)

Copied to clipboard

Jiu Sha, Mengxiao Zhu

Responsible & Trustworthy NLP

Challenge:	Structured Multilingual Reward Modeling Framework extends Reinforcement Learning with Verifiable Rewards (RLVR) to subjective and open-ended tasks.
Approach:	They propose a framework that extends Reinforcement Learning with Verifiable Rewards to subjective and open-ended tasks.
Outcome:	The proposed framework improves reasoning capability and response quality on 7 tasks across 50 low-resource languages.

DnDScore: Decontextualization and Decomposition for Factuality Verification in Long-Form Text Generation (2025.emnlp-main)

Copied to clipboard

Miriam Wanner, Benjamin Van Durme, Mark Dredze

Text Generation

Challenge:	Recent measures of factual precision use a decompose-then-verify framework . decontextualization is the process of augmenting subclaims with necessary context .
Approach:	They evaluate different decomposition, decontextualization and verification strategies . they introduce a deconstructualization aware verification method that validates subclaims in context .
Outcome:	The proposed method decomposes claims and independently verifyes them . it introduces a decontextualization aware verification method that validates subclaims in context .

Crossing the Reward Bridge: Expanding Reinforcement Learning with Verifiable Rewards Across Diverse Domains (2026.acl-long)

Copied to clipboard

Yi Su, Dian Yu, Linfeng Song, Juntao Li, Haitao Mi, Zhaopeng Tu, Min Zhang, Dong Yu

Challenge:	Reinforcement learning with verifiable rewards (RLVR) has been effective on structured tasks, but its reliance on simple, rule-based verifiers creates a bottleneck.
Approach:	They propose a framework that uses a generative verifier to provide soft, probabilistic rewards.
Outcome:	The proposed framework outperforms existing models up to 10x their size and can be scalable and effective.

GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning (2026.findings-acl)

Copied to clipboard

Yi Chen, Yuying Ge, Rui Wang, Yixiao Ge, Junhao Cheng, Ying Shan, Xihui Liu

Multimodality

Challenge:	Recent reinforcement learning approaches have advanced reasoning in Large Language Models (LLMs), yet their adaptation to multimodal LLMs remains underexplored.
Approach:	They propose a reinforcement learning framework that eliminates KL penalties and rewards consistency . they propose GRPO-CARE, which outperforms standard GR PO, with a base reward for accuracy and an adaptive bonus for consistency.
Outcome:	The proposed framework outperforms standard GRPO on the most difficult evaluation level and reasoning consistency test benchmarks.

Leveraging Outline-Optimized Generative Interactions and Critique for Self-Refining Outlines with Reinforcement Learning (2026.acl-long)

Copied to clipboard

Hengwei Liu, Haoyuan Ma, Qingqing Lyu, Daoxin Zhang, Yao Hu, Yongliang Shen, Yin Zhang, Weiming Lu

Challenge:	Logic-RL is a framework that transforms critique-guided outline refinement into a learnable policy through reinforcement learning.
Approach:	They propose a framework that transforms critique-guided outline refinement into a learnable policy through reinforcement learning.
Outcome:	The proposed framework improves on FreshWiki and WikiOutline . it can be iteratively applied, with improved quality continuing through three refinement rounds before diminishing returns.

Decomposition Dilemmas: Does Claim Decomposition Boost or Burden Fact-Checking Performance? (2025.naacl-long)

Copied to clipboard

Qisheng Hu, Quanyu Long, Wenya Wang

Responsible & Trustworthy NLP

Challenge:	Fact-checking pipelines adopt the Decompose-Then-Verify paradigm, where texts are broken down into smaller claims for individual verification and subsequently combined for a veracity decision.
Approach:	They propose to categorize decomposition errors and to reveal a trade-off between accuracy gains and noise introduced by decomposing.
Outcome:	The proposed analysis provides new insights into understanding current system’s instability and offers guidance for future studies toward improving claim decomposition in fact-checking pipelines.

AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation (2025.acl-long)

Copied to clipboard

Songming Zhang, Xue Zhang, Tong Zhang, Bojie Hu, Yufeng Chen, Jinan Xu

Semantic Text Processing

Challenge:	Existing methods for LLM alignment optimize tokens using a sparse, response-level reward or preference annotation.
Approach:	They propose an RLHF-equivalent distillation method for token-level reward optimization that incorporates the reward learned by DPO into the RLHG objective and builds a token-based teacher distribution.
Outcome:	The proposed method bridges the accuracy gap between the reward from the DPO model and the pure reward model by building a contrastive DPO reward with a normal and a reverse DPO.