# Steer LLM Latents for Hallucination Detection

arXiv: https://arxiv.org/abs/2503.01917 · HTML: https://mlsanity.com/paper/2503.01917/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 62 references that are in the map.
- First posted on arXiv 1 Mar 2025.

## Builds on (most cited first, 30 of 49)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [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)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (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)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [Object Hallucination in Image Captioning](https://mlsanity.com/paper/1809.02156/) (2018)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)

## Built on by (most cited first, 30 of 50)

- [SAFE: Multitask Failure Detection for Vision-Language-Action Models](https://mlsanity.com/paper/2506.09937/) (2025)
- [Large Language Models Hallucination: A Comprehensive Survey](https://mlsanity.com/paper/2510.06265/) (2025)
- [DynHD: Hallucination Detection for Diffusion Large Language Models via Denoising Dynamics Deviation Learning](https://mlsanity.com/paper/2603.16459/) (2026)
- [GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similarity](https://mlsanity.com/paper/2508.19972/) (2025)
- [Curveball Steering: The Right Direction To Steer Isn't Always Linear](https://mlsanity.com/paper/2603.09313/) (2026)
- [LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals](https://mlsanity.com/paper/2509.21875/) (2025)
- [Investigating CoT Monitorability in Large Reasoning Models](https://mlsanity.com/paper/2511.08525/) (2025)
- [Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring](https://mlsanity.com/paper/2605.30834/) (2026)
- [TraceDet: Hallucination Detection from the Decoding Trace of Diffusion Large Language Models](https://mlsanity.com/paper/2510.01274/) (2025)
- [TDGNet: Hallucination Detection in Diffusion Language Models via Temporal Dynamic Graphs](https://mlsanity.com/paper/2602.08048/) (2026)
- [Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning](https://mlsanity.com/paper/2510.02324/) (2025)
- [Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention](https://mlsanity.com/paper/2605.05892/) (2026)
- [HARP: Hallucination Detection via Reasoning Subspace Projection](https://mlsanity.com/paper/2509.11536/) (2025)
- [VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation](https://mlsanity.com/paper/2602.21054/) (2026)
- [LLM Hallucination Detection: A Fast Fourier Transform Method Based on Hidden Layer Temporal Signals](https://mlsanity.com/paper/2509.13154/) (2025)
- [Steering Large Reasoning Models towards Concise Reasoning via Flow Matching](https://mlsanity.com/paper/2602.05539/) (2026)
- [Student Guides Teacher: Weak-to-Strong Inference via Spectral Orthogonal Exploration](https://mlsanity.com/paper/2601.06160/) (2026)
- [LatentRefusal: Latent-Signal Refusal for Unanswerable Text-to-SQL Queries](https://mlsanity.com/paper/2601.10398/) (2026)
- [Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations](https://mlsanity.com/paper/2506.02696/) (2025)
- [Decoding Memories: An Efficient Pipeline for Self-Consistency Hallucination Detection](https://mlsanity.com/paper/2508.21228/) (2025)
- [TPA: Next Token Probability Attribution for Detecting Hallucinations in RAG](https://mlsanity.com/paper/2512.07515/) (2025)
- [OSCAR: Orchestrated Self-verification and Cross-path Refinement](https://mlsanity.com/paper/2604.01624/) (2026)
- [Hallucination Basins: A Dynamic Framework for Understanding and Controlling LLM Hallucinations](https://mlsanity.com/paper/2604.04743/) (2026)
- [Steering Conceptual Bias via Transformer Latent-Subspace Activation](https://mlsanity.com/paper/2506.18887/) (2025)
- [Grounding the Ungrounded: A Spectral-Graph Framework for Quantifying Hallucinations in Multimodal LLMs](https://mlsanity.com/paper/2508.19366/) (2025)
- [LLM Hallucination Detection: HSAD](https://mlsanity.com/paper/2509.23580/) (2025)
- [AP-OOD: Attention Pooling for Out-of-Distribution Detection](https://mlsanity.com/paper/2602.06031/) (2026)
- [SAKED: Mitigating Hallucination in Large Vision-Language Models via Stability-Aware Knowledge Enhanced Decoding](https://mlsanity.com/paper/2602.09825/) (2026)
- [Two Birds, One Projection: Harmonizing Safety and Utility in LVLMs via Inference-time Feature Projection](https://mlsanity.com/paper/2603.14825/) (2026)
- [GRADE: Probing Knowledge Gaps in LLMs through Gradient Subspace Dynamics](https://mlsanity.com/paper/2604.02830/) (2026)

## Abstract (arXiv)

Hallucinations in LLMs pose a significant concern to their safe deployment in real-world applications. Recent approaches have leveraged the latent space of LLMs for hallucination detection, but their embeddings, optimized for linguistic coherence rather than factual accuracy, often fail to clearly separate truthful and hallucinated content. To this end, we propose the Truthfulness Separator Vector (TSV), a lightweight and flexible steering vector that reshapes the LLM's representation space during inference to enhance the separation between truthful and hallucinated outputs, without altering model parameters. Our two-stage framework first trains TSV on a small set of labeled exemplars to form compact and well-separated clusters. It then augments the exemplar set with unlabeled LLM generations, employing an optimal transport-based algorithm for pseudo-labeling combined with a confidence-based filtering process. Extensive experiments demonstrate that TSV achieves state-of-the-art performance with minimal labeled data, exhibiting strong generalization across datasets and providing a practical solution for real-world LLM applications.