# Enhanced Language Model Truthfulness with Learnable Intervention and Uncertainty Expression

arXiv: https://arxiv.org/abs/2405.00301 · HTML: https://mlsanity.com/paper/2405.00301/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 31 references that are in the map.
- First posted on arXiv 1 May 2024.

## Builds on (most cited first, 25 of 25)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [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)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (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)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Trusting Your Evidence: Hallucinate Less with Context-aware Decoding](https://mlsanity.com/paper/2305.14739/) (2023)
- [RARR: Researching and Revising What Language Models Say, Using Language Models](https://mlsanity.com/paper/2210.08726/) (2022)
- [Prompting GPT-3 To Be Reliable](https://mlsanity.com/paper/2210.09150/) (2022)
- [A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation](https://mlsanity.com/paper/2307.03987/) (2023)
- [Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation](https://mlsanity.com/paper/2305.15852/) (2023)
- [Detecting and Mitigating Hallucinations in Multilingual Summarisation](https://mlsanity.com/paper/2305.13632/) (2023)
- [RHO (ρ): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding](https://mlsanity.com/paper/2212.01588/) (2022)
- [Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning](https://mlsanity.com/paper/2312.17484/) (2023)
- [LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses](https://mlsanity.com/paper/2310.19208/) (2023)
- [Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations](https://mlsanity.com/paper/2310.03951/) (2023)
- [Challenges with unsupervised LLM knowledge discovery](https://mlsanity.com/paper/2312.10029/) (2023)
- [FLEEK: Factual Error Detection and Correction with Evidence Retrieved from External Knowledge](https://mlsanity.com/paper/2310.17119/) (2023)
- [Information-Theoretic Text Hallucination Reduction for Video-grounded Dialogue](https://mlsanity.com/paper/2212.05765/) (2022)

## Built on by (most cited first, 6 of 6)

- [Enhancing Language Model Factuality via Activation-Based Confidence Calibration and Guided Decoding](https://mlsanity.com/paper/2406.13230/) (2024)
- [Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models](https://mlsanity.com/paper/2602.01654/) (2026)
- [From Weights to Activations: Is Steering the Next Frontier of Adaptation?](https://mlsanity.com/paper/2604.14090/) (2026)
- [Truth Neurons](https://mlsanity.com/paper/2505.12182/) (2025)
- [SCOPE: Sequential Conformal Probing for Reliable OOD Rejection in LLM Services](https://mlsanity.com/paper/2606.21255/) (2026)
- [TRACE: Trajectory Correction from Cross-layer Evidence for Hallucination Reduction](https://mlsanity.com/paper/2605.18163/) (2026)

## Abstract (arXiv)

Large language models (LLMs) can generate long-form and coherent text, yet they often hallucinate facts, which undermines their reliability. To mitigate this issue, inference-time methods steer LLM representations toward the "truthful directions" previously learned for truth elicitation. However, applying these truthful directions with the same intensity fails to generalize across different query contexts. We propose LITO, a Learnable Intervention method for Truthfulness Optimization that automatically identifies the optimal intervention intensity tailored to each specific context. LITO explores a sequence of model generations based on increasing levels of intervention intensities. It selects the most accurate response or refuses to answer when the predictions are highly uncertain. Experiments on multiple LLMs and question-answering datasets demonstrate that LITO improves truthfulness while preserving task accuracy. The adaptive nature of LITO counters the limitations of one-size-fits-all intervention methods, maximizing truthfulness by reflecting the model's internal knowledge only when it is confident. Our code is available at https://github.com/launchnlp/LITO.