mlsanityData to 7 Oct 2026

Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution

arXiv 2503.01695 ↗First posted 3 Mar 2025cs.CLcited by 7

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Improving context faithfulness in large language models is essential for developing trustworthy retrieval augmented generation systems and mitigating hallucinations, especially in long-form question answering (LFQA) tasks or scenarios involving knowledge conflicts. Existing methods either intervene LLMs only at inference without addressing their inherent limitations or overlook the potential for self-improvement. In this paper, we introduce GenDiE (Generate, Discriminate, Evolve), a novel self-evolving framework that enhances context faithfulness through fine-grained sentence-level optimization. GenDiE combines both generative and discriminative training, equipping LLMs with self-generation and self-scoring capabilities to facilitate iterative self-evolution. This supports both data construction for model alignment and score-guided search during inference. Furthermore, by treating each sentence in a response as an independent optimization unit, GenDiE effectively addresses the limitations of previous approaches that optimize at the holistic answer level, which may miss unfaithful details. Experiments on ASQA (in-domain LFQA) and ConFiQA (out-of-domain counterfactual QA) datasets demonstrate that GenDiE surpasses various baselines in both faithfulness and correctness, and exhibits robust performance for domain adaptation.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 34 of its 46 references that are in the map. First posted on arXiv 3 Mar 2025.

Builds on

34 of 46 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Groundedness in Retrieval-augmented Long-form Generation: An Empirical Study10 Apr
  2. 2024Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models22 Feb
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 31

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  5. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  6. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  7. 2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 895
  8. 2022Large Language Models Can Self-Improvecited by 656
  9. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
  10. 2019ELI5: Long Form Question Answeringcited by 567
  11. 2024ORPO: Monolithic Preference Optimization without Reference Modelcited by 556
  12. 2021Large Dual Encoders Are Generalizable Retrieverscited by 454
19 more
  1. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 385
  2. 2023Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflictscited by 333
  3. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 319
  4. 2023Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervisioncited by 318
  5. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 296
  6. 2023AlignScore: Evaluating Factual Consistency with a Unified Alignment Functioncited by 284
  7. 2024Knowledge Conflicts for LLMs: A Surveycited by 274
  8. 2024Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMscited by 265
  9. 2022ASQA: Factoid Questions Meet Long-Form Answerscited by 231
  10. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 204
  11. 2023A Critical Evaluation of Evaluations for Long-form Question Answeringcited by 111
  12. 2024Context-DPO: Aligning Language Models for Context-Faithfulnesscited by 50
  13. 2023Effective Large Language Model Adaptation for Improved Grounding and Citation Generationcited by 44
  14. 2024Training Language Models to Generate Text with Citations via Fine-grained Rewardscited by 40
  15. 2024SFR-RAG: Towards Contextually Faithful LLMscited by 19
  16. 2023A Two-Stage Adaptation of Large Language Models for Text Rankingcited by 17
  17. 2024Self-Evolved Reward Learning for LLMscited by 16
  18. 2023Natural Language Embedded Programs for Hybrid Language Symbolic Reasoningcited by 15
  19. 2024Learning to Generate Answers with Citations via Factual Consistency Modelscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 1.

7 papers.

  1. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  2. 2025Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learningcited by 7
  3. 2026TreePS-RAG: Tree-based Process Supervision for Reinforcement Learning in Agentic RAGcited by 5
  4. 2025Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generationcited by 2
  5. 2025Copy-Paste to Mitigate Large Language Model Hallucinationscited by 1
  6. 2025RAG-Zeval: Towards Robust and Interpretable Evaluation on RAG Responses through End-to-End Rule-Guided Reasoningcited by 0
  7. 2025MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains
  2. 2025SSFO: Self-Supervised Faithfulness Optimization for Retrieval-Augmented Generation
  3. 2025Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization
  4. 2026Learning to Self-Evolve
  5. 2024LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering
  6. 2025A-SEA3L-QA: A Fully Automated Self-Evolving, Adversarial Workflow for Arabic Long-Context Question-Answer Generation
  7. 2026Trust or Abstain? A Self-Aware RAG Approach
  8. 2026Questioning the Questions: Sustaining Self-Evolution in Reasoning Models