Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality

• URL: http://arxiv.org/abs/2509.23765v2
• Date: Sat, 11 Oct 2025 03:51:40 GMT
• Title: Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality
• Authors: Junliang Li, Yucheng Wang, Yan Chen, Yu Ran, Ruiqing Zhang, Jing Liu, Hua Wu, Haifeng Wang,
• Abstract summary: Hallucination and factuality deficits remain key obstacles to the reliability of large language models.<n>We propose a novel framework that focuses on the knowledge consistency between the policy model's expressed knowledge and the base model's parametric knowledge.
• Score: 27.687276551678583
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Hallucination and factuality deficits remain key obstacles to the reliability of large language models (LLMs) in long-form generation. Existing reinforcement learning from human feedback (RLHF) frameworks primarily rely on preference rewards, yet they often overlook the model's internal knowledge boundaries, exacerbating the so-called "hallucination tax". To address this challenge, we propose Knowledge-Level Consistency Reinforcement Learning Framework (KLCF), a novel framework that focuses on the knowledge consistency between the policy model's expressed knowledge and the base model's parametric knowledge, and introduces a Dual-Fact Alignment mechanism to jointly optimize factual recall and precision. Specifically, KLCF leverages pretrained knowledge boundaries to construct fact checklist, guiding online reinforcement learning to improve factual coverage and recall; simultaneously, it trains a self-assessment module based on the base model's internal knowledge to enhance factual precision during generation. Unlike prior methods that rely on external retrieval or heavy verification, our reward design is fully external-knowledge-free and lightweight, making KLCF efficient and easily scalable to large-scale training. Experimental results demonstrate that KLCF substantially improves factuality metrics across multiple long-form benchmarks and effectively alleviates model hallucinations.

Related papers

• Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models [80.21037538996553]
  We propose a novel meta-cognitive framework for reliable knowledge augmentation via differentiated intervention and alignment.<n>Our approach leverages internal cognitive signals to partition the knowledge space into mastered, confused, and missing regions, guiding targeted knowledge expansion.<n>Our framework consistently outperforms strong baselines, validating its rationality in not only enhancing knowledge capabilities but also fostering cognitive behaviors that better distinguish knowns from unknowns.
  arXiv  Detail & Related papers  (2026-02-13T15:07:35Z)
• EtCon: Edit-then-Consolidate for Reliable Knowledge Editing [85.20993502078899]
  We propose Edit-then-Consolidate, a novel knowledge editing paradigm that aims to bridge the gap between theoretical knowledge editing methods and their real-world applicability.<n>Our framework consistently improves editing reliability and generalization under real-world evaluations, while better preserving locality and pre-trained capabilities.
  arXiv  Detail & Related papers  (2025-12-04T12:43:50Z)
• CLLMRec: LLM-powered Cognitive-Aware Concept Recommendation via Semantic Alignment and Prerequisite Knowledge Distillation [3.200298153814017]
  The growth of Massive Open Online Courses (MOOCs) presents significant challenges for personalized learning, where concept is crucial.<n>Existing approaches typically rely on heterogeneous information networks or knowledge graphs to capture conceptual relationships, combined with knowledge tracing models to assess learners' cognitive states.<n>This paper proposes CLLMRec, a novel framework that leverages Large Language Models to generate personalized concept recommendations.
  arXiv  Detail & Related papers  (2025-11-21T08:37:39Z)
• TRAIL: Joint Inference and Refinement of Knowledge Graphs with Large Language Models [5.678291291711662]
  TRAIL is a novel, unified framework for Thinking, Reasoning, And Incremental Learning.<n>It couples joint inference and dynamic KG refinement with large language models.<n>Extensive experiments on multiple benchmarks demonstrate that TRAIL outperforms existing KG-augmented and retrieval-augmented LLM baselines by 3% to 13%.
  arXiv  Detail & Related papers  (2025-08-06T14:25:05Z)
• Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling [48.15636223774418]
  Large language models (LLMs) are prone to hallucination stemming from misaligned self-awareness.<n>We propose the Explicit Knowledge Boundary Modeling framework to integrate fast and slow reasoning systems to harmonize reliability and usability.
  arXiv  Detail & Related papers  (2025-03-04T03:16:02Z)
• Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization [49.95746521480879]
  We introduce PKUE (Precise Knowledge Utilization Enhancement), which fine-tunes the model on self-generated responses to precise and simple factual questions.<n>Extensive experiments demonstrate that PKUE significantly improves LLM overall performance.
  arXiv  Detail & Related papers  (2025-02-26T13:34:52Z)
• Decoding Knowledge in Large Language Models: A Framework for Categorization and Comprehension [14.039653386385519]
  Large language models (LLMs) acquire, retain, and apply knowledge.<n>This paper introduces a novel framework, K-(CSA)2, which categorizes LLM knowledge along two dimensions: correctness and confidence.
  arXiv  Detail & Related papers  (2025-01-02T16:34:10Z)
• Gradual Learning: Optimizing Fine-Tuning with Partially Mastered Knowledge in Large Language Models [51.20499954955646]
  Large language models (LLMs) acquire vast amounts of knowledge from extensive text corpora during the pretraining phase. In later stages such as fine-tuning and inference, the model may encounter knowledge not covered in the initial training. We propose a two-stage fine-tuning strategy to improve the model's overall test accuracy and knowledge retention.
  arXiv  Detail & Related papers  (2024-10-08T08:35:16Z)
• Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback [14.120154004011084]
  Large Language Models (LLMs) often generate erroneous outputs, known as hallucinations. We present a novel alignment framework called Reinforcement Learning from Knowledge Feedback (RLKF)
  arXiv  Detail & Related papers  (2024-03-27T08:39:56Z)
• Knowledge Verification to Nip Hallucination in the Bud [69.79051730580014]
  We demonstrate the feasibility of mitigating hallucinations by verifying and minimizing the inconsistency between external knowledge present in the alignment data and the intrinsic knowledge embedded within foundation LLMs. We propose a novel approach called Knowledge Consistent Alignment (KCA), which employs a well-aligned LLM to automatically formulate assessments based on external knowledge. We demonstrate the superior efficacy of KCA in reducing hallucinations across six benchmarks, utilizing foundation LLMs of varying backbones and scales.
  arXiv  Detail & Related papers  (2024-01-19T15:39:49Z)
• A Comprehensive Study of Knowledge Editing for Large Language Models [82.65729336401027]
  Large Language Models (LLMs) have shown extraordinary capabilities in understanding and generating text that closely mirrors human communication. This paper defines the knowledge editing problem and provides a comprehensive review of cutting-edge approaches. We introduce a new benchmark, KnowEdit, for a comprehensive empirical evaluation of representative knowledge editing approaches.
  arXiv  Detail & Related papers  (2024-01-02T16:54:58Z)

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.