mlsanityData to 14 Oct 2026

Enhancing Language Model Factuality via Activation-Based Confidence Calibration and Guided Decoding

arXiv 2406.13230 ↗First posted 19 Jun 2024cs.CLcited by 14

Not on the map. Why?

Abstract (arXiv)

Calibrating language models (LMs) aligns their generation confidence with the actual likelihood of answer correctness, which can inform users about LMs' reliability and mitigate hallucinated content. However, prior calibration methods, such as self-consistency-based and logit-based approaches, are either limited in inference-time efficiency or fall short of providing informative signals. Moreover, simply filtering out low-confidence responses reduces the LM's helpfulness when the answers are correct. Therefore, effectively using calibration techniques to enhance an LM's factuality remains an unsolved challenge. In this paper, we first propose an activation-based calibration method, ActCab, which trains a linear layer on top of the LM's last-layer activations that can better capture the representations of knowledge. Built on top of ActCab, we further propose CoDec, a confidence-guided decoding strategy to elicit truthful answers with high confidence from LMs. By evaluating on five popular QA benchmarks, ActCab achieves superior calibration performance than all competitive baselines, e.g., by reducing the average expected calibration error (ECE) score by up to 39%. Further experiments on CoDec show consistent improvements in several LMs' factuality on challenging QA datasets, such as TruthfulQA, highlighting the value of confidence signals in enhancing factuality.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 21 of its 28 references that are in the map. First posted on arXiv 19 Jun 2024.

Builds on

21 of 28 references.

References · 21

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  4. 2017On Calibration of Modern Neural Networkscited by 4,960
  5. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  6. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  7. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,336
  8. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  9. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,302
  10. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 974
  11. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 812
  12. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 767
9 more
  1. 2017Crowdsourcing Multiple Choice Science Questionscited by 765
  2. 2022Teaching Models to Express Their Uncertainty in Wordscited by 751
  3. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 445
  4. 2022Prompting GPT-3 To Be Reliablecited by 260
  5. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 197
  6. 2023LitCab: Lightweight Language Model Calibration over Short- and Long-form Responsescited by 44
  7. 2023GRACE: Discriminator-Guided Chain-of-Thought Reasoningcited by 35
  8. 2023On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Studycited by 25
  9. 2024Enhanced Language Model Truthfulness with Learnable Intervention and Uncertainty Expressioncited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 7.

14 papers.

Sort:

By area:

  1. 2025Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Modelscited by 16
  2. 2025Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Reviewcited by 4
  3. 2025MedVAL: Toward Expert-Level Medical Text Validation with Language Modelscited by 3
  4. 2026Just how sure are you? Improving Verbalized Uncertainty Calibration in Medical VQAcited by 3
  5. 2025REHEARSE: Experiential Rehearsal for Verbal Confidence Calibration in Large Language Modelscited by 2
  6. 2026How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoningcited by 2
  7. 2026Structuring the Space of Sociotechnical Alignmentcited by 2
  8. 2025Deep Hidden Cognition Facilitates Reliable Chain-of-Thought Reasoningcited by 1
  9. 2025Open the Oyster: Empirical Evaluation and Improvement of Code Reasoning Confidence in LLMscited by 1
  10. 2026Confidence Should Be Calibrated More Than One Turn Deepcited by 1
  11. 2025The Effects of Data Augmentation on Confidence Estimation for LLMscited by 0
  12. 2026Fine-grained Approaches for Confidence Calibration of LLMs in Automated Code Revisioncited by 0
2 more
  1. 2026Assessing and Mitigating Miscalibration in LLM-Based Social Science Measurementcited by 0
  2. 2026Calibration, Not Answer Selection: Distilling Internal Confidence in Reasoning Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Calibrating the Confidence of Large Language Models by Eliciting Fidelity
  2. 2026ConfidenceBench: Evaluating Confidence Calibration in Large Language Models
  3. 2024Calibrating Long-form Generations from Large Language Models
  4. 2025Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models
  5. 2026Closing the Confidence-Faithfulness Gap in Large Language Models
  6. 2026NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systems
  7. 2026CALIBER: Calibrating Confidence Before and After Reasoning in Language Models
  8. 2026Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning