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

arXiv: https://arxiv.org/abs/2406.13230 · HTML: https://mlsanity.com/paper/2406.13230/

## 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 (most cited first, 21 of 21)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback](https://mlsanity.com/paper/2305.14975/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Crowdsourcing Multiple Choice Science Questions](https://mlsanity.com/paper/1707.06209/) (2017)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering](https://mlsanity.com/paper/2012.00955/) (2020)
- [Prompting GPT-3 To Be Reliable](https://mlsanity.com/paper/2210.09150/) (2022)
- [Out-of-Distribution Detection and Selective Generation for Conditional Language Models](https://mlsanity.com/paper/2209.15558/) (2022)
- [LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses](https://mlsanity.com/paper/2310.19208/) (2023)
- [GRACE: Discriminator-Guided Chain-of-Thought Reasoning](https://mlsanity.com/paper/2305.14934/) (2023)
- [On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Study](https://mlsanity.com/paper/2304.08653/) (2023)
- [Enhanced Language Model Truthfulness with Learnable Intervention and Uncertainty Expression](https://mlsanity.com/paper/2405.00301/) (2024)

## Built on by (most cited first, 14 of 14)

- [Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Models](https://mlsanity.com/paper/2501.09997/) (2025)
- [Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review](https://mlsanity.com/paper/2504.18346/) (2025)
- [MedVAL: Toward Expert-Level Medical Text Validation with Language Models](https://mlsanity.com/paper/2507.03152/) (2025)
- [Just how sure are you? Improving Verbalized Uncertainty Calibration in Medical VQA](https://mlsanity.com/paper/2606.27023/) (2026)
- [REHEARSE: Experiential Rehearsal for Verbal Confidence Calibration in Large Language Models](https://mlsanity.com/paper/2508.14390/) (2025)
- [How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2602.02103/) (2026)
- [Structuring the Space of Sociotechnical Alignment](https://mlsanity.com/paper/2607.01250/) (2026)
- [Deep Hidden Cognition Facilitates Reliable Chain-of-Thought Reasoning](https://mlsanity.com/paper/2507.10007/) (2025)
- [Open the Oyster: Empirical Evaluation and Improvement of Code Reasoning Confidence in LLMs](https://mlsanity.com/paper/2511.02197/) (2025)
- [Confidence Should Be Calibrated More Than One Turn Deep](https://mlsanity.com/paper/2604.05397/) (2026)
- [The Effects of Data Augmentation on Confidence Estimation for LLMs](https://mlsanity.com/paper/2506.11046/) (2025)
- [Fine-grained Approaches for Confidence Calibration of LLMs in Automated Code Revision](https://mlsanity.com/paper/2604.06723/) (2026)
- [Assessing and Mitigating Miscalibration in LLM-Based Social Science Measurement](https://mlsanity.com/paper/2605.11954/) (2026)
- [Calibration, Not Answer Selection: Distilling Internal Confidence in Reasoning Models](https://mlsanity.com/paper/2609.33290/) (2026)

## 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.