mlsanityData to 7 Oct 2026

SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs

arXiv 2503.03032 ↗First posted 4 Mar 2025cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

Despite the state-of-the-art performance of Large Language Models (LLMs), these models often suffer from hallucinations, which can undermine their performance in critical applications. In this work, we propose SAFE, a novel method for detecting and mitigating hallucinations by leveraging Sparse Autoencoders (SAEs). While hallucination detection techniques and SAEs have been explored independently, their synergistic application in a comprehensive system, particularly for hallucination-aware query enrichment, has not been fully investigated. To validate the effectiveness of SAFE, we evaluate it on two models with available SAEs across three diverse cross-domain datasets designed to assess hallucination problems. Empirical results demonstrate that SAFE consistently improves query generation accuracy and mitigates hallucinations across all datasets, achieving accuracy improvements of up to 29.45%.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 24 of its 49 references that are in the map. First posted on arXiv 4 Mar 2025.

Builds on

24 of 49 references.

References · 24

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2020Scaling Laws for Neural Language Modelscited by 6,411
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  4. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  5. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  6. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,928
  7. 2023Sparse Autoencoders Find Highly Interpretable Features in Language Modelscited by 1,359
  8. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
  9. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,219
  10. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  11. 2023LIMA: Less Is More for Alignmentcited by 1,080
  12. 2022Toy Models of Superpositioncited by 928
12 more
  1. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 733
  2. 2023Textbooks Are All You Need II: phi-1.5 technical reportcited by 559
  3. 2021SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarizationcited by 402
  4. 2024Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2cited by 381
  5. 2023FreshLLMs: Refreshing Large Language Models with Search Engine Augmentationcited by 308
  6. 2023MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Datacited by 282
  7. 2023Alleviating Hallucinations of Large Language Models through Induced Hallucinationscited by 78
  8. 2024RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representationscited by 77
  9. 2024LLMs Will Always Hallucinate, and We Need to Live With Thiscited by 77
  10. 2023UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluationcited by 74
  11. 2023Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuningcited by 45
  12. 2024Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEscited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 4.

7 papers.

  1. 2025Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEscited by 14
  2. 2025Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safetycited by 10
  3. 2025Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoderscited by 6
  4. 2026NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labelscited by 3
  5. 2026HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoderscited by 3
  6. 2026Interpretability Transfer from Language to Vision via Sparse Autoencoderscited by 1
  7. 2026Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussionscited by 0