mlsanityData to 14 Oct 2026

Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection

arXiv 2403.09972 ↗First posted 15 Mar 2024cs.CLcited by 41

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Self-detection for Large Language Models (LLMs) seeks to evaluate the trustworthiness of the LLM's output by leveraging its own capabilities, thereby alleviating the issue of output hallucination. However, existing self-detection approaches only retrospectively evaluate answers generated by LLM, typically leading to the over-trust in incorrectly generated answers. To tackle this limitation, we propose a novel self-detection paradigm that considers the comprehensive answer space beyond LLM-generated answers. It thoroughly compares the trustworthiness of multiple candidate answers to mitigate the over-trust in LLM-generated incorrect answers. Building upon this paradigm, we introduce a two-step framework, which firstly instructs LLM to reflect and provide justifications for each candidate answer, and then aggregates the justifications for comprehensive target answer evaluation. This framework can be seamlessly integrated with existing approaches for superior self-detection. Extensive experiments on six datasets spanning three tasks demonstrate the effectiveness of the proposed framework.

Key facts. Cited by 41 papers in the map (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 47 of its 57 references that are in the map. First posted on arXiv 15 Mar 2024.

Builds on

47 of 57 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023Large Language Models Cannot Self-Correct Reasoning Yet3 Oct
  2. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies6 Aug
  3. 2023SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning1 Aug
  4. 2023Self-Evaluation Guided Beam Search for Reasoning1 May
  5. 2022Large Language Models Can Self-Improve20 Oct
  6. 2022Language Models (Mostly) Know What They Know11 Jul

Other references · 41

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  4. 2017On Calibration of Modern Neural Networkscited by 4,960
  5. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  6. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  7. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,883
  8. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  9. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,822
  10. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,302
  11. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  12. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,031
29 more
  1. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 974
  2. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 894
  3. 2019Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inferencecited by 876
  4. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 812
  5. 2022Teaching Models to Express Their Uncertainty in Wordscited by 751
  6. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 445
  7. 2019Learning the Difference that Makes a Difference with Counterfactually-Augmented Datacited by 439
  8. 2020Calibration of Pre-trained Transformerscited by 315
  9. 2022Large Language Models are Better Reasoners with Self-Verificationcited by 307
  10. 2022Prompting GPT-3 To Be Reliablecited by 260
  11. 2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 239
  12. 2022Making Large Language Models Better Reasoners with Step-Aware Verifiercited by 233
  13. 2023Fine-tuning Language Models for Factualitycited by 221
  14. 2024Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaborationcited by 180
  15. 2022ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoningcited by 177
  16. 2023Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verificationcited by 166
  17. 2022Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanationscited by 159
  18. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 147
  19. 2023Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Frameworkcited by 139
  20. 2023Deductive Verification of Chain-of-Thought Reasoningcited by 124
  21. 2023Do Language Models Know When They're Hallucinating References?cited by 116
  22. 2023Decomposing Uncertainty for Large Language Models through Input Clarification Ensemblingcited by 114
  23. 2023Learning From Mistakes Makes LLM Better Reasonercited by 101
  24. 2023SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistencycited by 90
  25. 2023Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Methodcited by 51
  26. 2023Uncertainty in Natural Language Processing: Sources, Quantification, and Applicationscited by 44
  27. 2023GRACE: Discriminator-Guided Chain-of-Thought Reasoningcited by 35
  28. 2023On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Studycited by 25
  29. 2023A Study on the Calibration of In-context Learningcited by 22

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 10; 2025: 18; 2026: 13.

41 papers.

Sort:

By area:

  1. 2024To Believe or Not to Believe Your LLMcited by 120
  2. 2025Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Abovecited by 52
  3. 2025Large Language Models Hallucination: A Comprehensive Surveycited by 49
  4. 2024Knowledge Boundary of Large Language Models: A Surveycited by 40
  5. 2024Cycles of Thought: Measuring LLM Confidence through Stable Explanationscited by 29
  6. 2024SPRIG: Improving Large Language Model Performance by System Prompt Optimizationcited by 29
  7. 2024Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMscited by 23
  8. 2024Enhancing Confidence Expression in Large Language Models Through Learning from Past Experiencecited by 21
  9. 2025Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?cited by 16
  10. 2025WiCkeD: A Simple Method to Make Multiple Choice Benchmarks More Challengingcited by 11
  11. 2025Do not Abstain! Identify and Solve the Uncertaintycited by 11
  12. 2024Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandemcited by 9
29 more
  1. 2024Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modelingcited by 9
  2. 2025C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Modelscited by 9
  3. 2025Advancing the Scientific Method with Large Language Models: From Hypothesis to Discoverycited by 7
  4. 2025Self-Evaluating LLMs for Multi-Step Tasks: Stepwise Confidence Estimation for Failure Detectioncited by 6
  5. 2026ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinementcited by 5
  6. 2025Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Reviewcited by 4
  7. 2026Instinct vs. Reflection: Unifying Token and Verbalized Confidence in Multimodal Large Modelscited by 4
  8. 2024MSCoTDet: Language-driven Multi-modal Fusion for Improved Multispectral Pedestrian Detectioncited by 3
  9. 2024Topic Classification of Case Law Using a Large Language Model and a New Taxonomy for UK Law: AI Insights into Summary Judgmentcited by 3
  10. 2026MM-StanceDet: Retrieval-Augmented Multi-modal Multi-agent Stance Detectioncited by 3
  11. 2025Uncertainty-Aware Adaptation of Large Language Models for Protein-Protein Interaction Analysiscited by 2
  12. 2025PromptPrism: A Linguistically-Inspired Taxonomy for Promptscited by 2
  13. 2025AGENT-X: Adaptive Guideline-based Expert Network for Threshold-free AI-generated teXt detectioncited by 2
  14. 2025Beware of Reasoning Overconfidence: Pitfalls in the Reasoning Process for Multi-solution Taskscited by 2
  15. 2026Recursive Think-Answer Process for LLMs and VLMscited by 2
  16. 2026VecCISC: Improving Confidence-Informed Self-Consistency with Reasoning Trace Clustering and Candidate Answer Selectioncited by 2
  17. 2026A Systematic Evaluation of Black-Box Uncertainty Estimation Methods for Large Language Modelscited by 2
  18. 2025Optimizing Chain-of-Thought Confidence via Topological and Dirichlet Risk Analysiscited by 1
  19. 2026Reducing Hallucinations in LLM-based Scientific Literature Analysis Using Peer Context Outlier Detectioncited by 1
  20. 2025Decoding Knowledge in Large Language Models: A Framework for Categorization and Comprehensioncited by 0
  21. 2025Know Your Mistakes: Towards Preventing Overreliance on Task-Oriented Conversational AI Through Accountability Modelingcited by 0
  22. 2025Large Language Models in the Task of Automatic Validation of Text Classifier Predictionscited by 0
  23. 2025GradeSQL: Test-Time Inference with Outcome Reward Models for Text-to-SQL Generation from Large Language Modelscited by 0
  24. 2026Deep Learning-based Method for Expressing Knowledge Boundary of Black-Box LLMcited by 0
  25. 2026Clustered Self-Assessment: A Simple yet Effective Method for Uncertainty Quantification in Large Language Modelscited by 0
  26. 2026Adaptive and Explicit safe: Triggering Latent Safety Awareness in Large Reasoning Modelscited by 0
  27. 2026Can You Trust the Confidence? ConfBench for Vision-Language Models on Document Extractioncited by 0
  28. 2026The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstainingcited by 0
  29. 2026Sieve and Sage: Efficient Distraction Filtering for Reliable RALM Abstentioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025The Self-Execution Benchmark: Measuring LLMs' Attempts to Overcome Their Lack of Self-Execution
  2. 2025After Retrieval, Before Generation: Enhancing the Trustworthiness of Large Language Models in Retrieval-Augmented Generation
  3. 2024Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations
  4. 2026Self-Verified Distillation: Your Language Model Is Secretly Its Own Synthetic Data Pipeline
  5. 2026Trust or Abstain? A Self-Aware RAG Approach
  6. 2024Large Language Models Can Self-Improve in Long-context Reasoning
  7. 2024Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs
  8. 2025The Self-Improvement Paradox: Can Language Models Bootstrap Reasoning Capabilities without External Scaffolding?