# TruthFlow: Truthful LLM Generation via Representation Flow Correction

arXiv: https://arxiv.org/abs/2502.04556 · HTML: https://mlsanity.com/paper/2502.04556/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Feb 2025.

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

- [ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment](https://mlsanity.com/paper/2602.17560/) (2026)
- [Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention](https://mlsanity.com/paper/2605.05892/) (2026)
- [Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generation](https://mlsanity.com/paper/2503.03106/) (2025)
- [Steering Large Reasoning Models towards Concise Reasoning via Flow Matching](https://mlsanity.com/paper/2602.05539/) (2026)
- [PreFlect: From Retrospective to Prospective Reflection in Large Language Model Agents](https://mlsanity.com/paper/2602.07187/) (2026)
- [Focus on What Matters: Enhancing Medical Vision-Language Models with Automatic Attention Alignment Tuning](https://mlsanity.com/paper/2505.18503/) (2025)
- [LayerCake: Token-Aware Contrastive Decoding within Large Language Model Layers](https://mlsanity.com/paper/2507.04404/) (2025)
- [Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior](https://mlsanity.com/paper/2606.08454/) (2026)
- [FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models](https://mlsanity.com/paper/2604.15488/) (2026)
- [Conditional Optimal Bridge for Riemannian Activation Steering](https://mlsanity.com/paper/2607.10517/) (2026)
- [Direct Multi-Token Decoding](https://mlsanity.com/paper/2510.11958/) (2025)
- [Listen to the Layers: Mitigating Hallucinations with Inter-Layer Disagreement](https://mlsanity.com/paper/2602.09486/) (2026)
- [BarrierSteer: LLM Safety via Learning Barrier Steering](https://mlsanity.com/paper/2602.20102/) (2026)
- [Can Factual Opinions Be Edited (Manipulated) in Large Language Models?](https://mlsanity.com/paper/2606.03096/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are known to struggle with consistently generating truthful responses. While various representation intervention techniques have been proposed, these methods typically apply a universal representation correction vector to all input queries, limiting their effectiveness against diverse queries in practice. In this study, we introduce TruthFlow, a novel method that leverages the Flow Matching technique for query-specific truthful representation correction. Specifically, TruthFlow first uses a flow model to learn query-specific correction vectors that transition representations from hallucinated to truthful states. Then, during inference, the trained flow model generates these correction vectors to enhance the truthfulness of LLM outputs. Experimental results demonstrate that TruthFlow significantly improves performance on open-ended generation tasks across various advanced LLMs evaluated on TruthfulQA. Moreover, the trained TruthFlow model exhibits strong transferability, performing effectively on other unseen hallucination benchmarks.