mlsanityData to 14 Oct 2026

Improving Factuality with Explicit Working Memory

arXiv 2412.18069 ↗First posted 24 Dec 2024cs.CLcited by 10

Not on the map. Why?

Abstract (arXiv)

Large language models can generate factually inaccurate content, a problem known as hallucination. Recent works have built upon retrieved-augmented generation to improve factuality through iterative prompting but these methods are limited by the traditional RAG design. To address these challenges, we introduce EWE (Explicit Working Memory), a novel approach that enhances factuality in long-form text generation by integrating a working memory that receives real-time feedback from external resources. The memory is refreshed based on online fact-checking and retrieval feedback, allowing EWE to rectify false claims during the generation process and ensure more accurate and reliable outputs. Our experiments demonstrate that Ewe outperforms strong baselines on four fact-seeking long-form generation datasets, increasing the factuality metric, VeriScore, by 2 to 6 points absolute without sacrificing the helpfulness of the responses. Further analysis reveals that the design of rules for memory updates, configurations of memory units, and the quality of the retrieval datastore are crucial factors for influencing model performance.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 26 of its 34 references that are in the map. First posted on arXiv 24 Dec 2024.

Builds on

26 of 34 references.

References · 26

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  6. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  7. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  8. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  9. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  10. 2023AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedbackcited by 748
  11. 2023OpenAssistant Conversations -- Democratizing Large Language Model Alignmentcited by 721
  12. 2023Active Retrieval Augmented Generationcited by 516
14 more
  1. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  2. 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 324
  3. 2022Memorizing Transformerscited by 226
  4. 2024Long-form factuality in large language modelscited by 155
  5. 2024Fine-grained Hallucination Detection and Editing for Language Modelscited by 149
  6. 2024VERISCORE: Evaluating the factuality of verifiable claims in long-form text generationcited by 117
  7. 2024DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Modelscited by 63
  8. 2024TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Textcited by 63
  9. 2024Scaling Retrieval-Based Language Models with a Trillion-Token Datastorecited by 56
  10. 2024FLAME: Factuality-Aware Alignment for Large Language Modelscited by 47
  11. 2024Memory3: Language Modeling with Explicit Memorycited by 40
  12. 2023Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectificationcited by 38
  13. 2024Nearest Neighbor Speculative Decoding for LLM Generation and Attributioncited by 25
  14. 2024RAC: Efficient LLM Factuality Correction with Retrieval Augmentationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 2.

10 papers.

  1. 2025AbstentionBench: Reasoning LLMs Fail on Unanswerable Questionscited by 145
  2. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 50
  3. 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topicscited by 36
  4. 2025A Review of Incorporating Psychological Theories in LLMscited by 6
  5. 2025FACTORY: A Challenging Human-Verified Prompt Set for Long-Form Factualitycited by 6
  6. 2025Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitationcited by 5
  7. 2025MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Modelscited by 4
  8. 2026VerifAI: A Verifiable Open-Source Search Engine for Biomedical Question Answeringcited by 1
  9. 2025HA-RAG: Hotness-Aware RAG Acceleration via Mixed Precision and Data Placementcited by 0
  10. 2026MIRAGE: Defending Long-Form RAG Against Misinformation Pollutioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Models
  2. 2025FactReasoner: A Probabilistic Approach to Long-Form Factuality Assessment for Large Language Models
  3. 2024Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown
  4. 2024FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation
  5. 2023Fine-tuning Language Models for Factuality
  6. 2025Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generation
  7. 2025The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality
  8. 2025Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals