# Mitigating Large Language Model Hallucination with Faithful Finetuning

arXiv: https://arxiv.org/abs/2406.11267 · HTML: https://mlsanity.com/paper/2406.11267/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 40 references that are in the map.
- First posted on arXiv 17 Jun 2024.

## Builds on (most cited first, 30 of 31)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [Trusting Your Evidence: Hallucinate Less with Context-aware Decoding](https://mlsanity.com/paper/2305.14739/) (2023)
- [Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics](https://mlsanity.com/paper/2104.13346/) (2021)
- [Fine-tuning Language Models for Factuality](https://mlsanity.com/paper/2311.08401/) (2023)
- [A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation](https://mlsanity.com/paper/2307.03987/) (2023)
- [On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?](https://mlsanity.com/paper/2204.07931/) (2022)
- [Generating Benchmarks for Factuality Evaluation of Language Models](https://mlsanity.com/paper/2307.06908/) (2023)
- [Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus](https://mlsanity.com/paper/2311.13230/) (2023)
- [TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space](https://mlsanity.com/paper/2402.17811/) (2024)
- [Towards Mitigating Hallucination in Large Language Models via Self-Reflection](https://mlsanity.com/paper/2310.06271/) (2023)
- [The Factual Inconsistency Problem in Abstractive Text Summarization: A Survey](https://mlsanity.com/paper/2104.14839/) (2021)
- [Alleviating Hallucinations of Large Language Models through Induced Hallucinations](https://mlsanity.com/paper/2312.15710/) (2023)
- [Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Better](https://mlsanity.com/paper/2212.08597/) (2022)
- [UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation](https://mlsanity.com/paper/2303.08518/) (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)
- [DelucionQA: Detecting Hallucinations in Domain-specific Question Answering](https://mlsanity.com/paper/2312.05200/) (2023)
- [Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations](https://mlsanity.com/paper/2403.18167/) (2024)
- [Teaching Language Models to Hallucinate Less with Synthetic Tasks](https://mlsanity.com/paper/2310.06827/) (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)
- [SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully](https://mlsanity.com/paper/2401.05930/) (2024)
- [Encouraging Neural Machine Translation to Satisfy Terminology Constraints](https://mlsanity.com/paper/2106.03730/) (2021)

## Built on by (most cited first, 24 of 24)

- [Large Language Models Hallucination: A Comprehensive Survey](https://mlsanity.com/paper/2510.06265/) (2025)
- [Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering](https://mlsanity.com/paper/2409.10790/) (2024)
- [LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits](https://mlsanity.com/paper/2502.08141/) (2025)
- [Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination](https://mlsanity.com/paper/2410.17477/) (2024)
- [HalluRNN: Mitigating Hallucinations via Recurrent Cross-Layer Reasoning in Large Vision-Language Models](https://mlsanity.com/paper/2506.17587/) (2025)
- [From Extraction to Synthesis: Entangled Heuristics for Agent-Augmented Strategic Reasoning](https://mlsanity.com/paper/2507.13768/) (2025)
- [Exposing Hallucinations To Suppress Them: VLMs Representation Editing With Generative Anchors](https://mlsanity.com/paper/2509.21997/) (2025)
- [The Illusionist's Prompt: Exposing the Factual Vulnerabilities of Large Language Models with Linguistic Nuances](https://mlsanity.com/paper/2504.02865/) (2025)
- [HalluScore: Large Language Model Hallucination Question Answering Benchmark](https://mlsanity.com/paper/2605.17007/) (2026)
- [Learning Auxiliary Tasks Improves Reference-Free Hallucination Detection in Open-Domain Long-Form Generation](https://mlsanity.com/paper/2505.12265/) (2025)
- [FaithSCAN: Model-Driven Single-Pass Hallucination Detection for Faithful Visual Question Answering](https://mlsanity.com/paper/2601.00269/) (2026)
- [Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research](https://mlsanity.com/paper/2604.17843/) (2026)
- [Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding](https://mlsanity.com/paper/2604.22335/) (2026)
- [An Evolutionary Large Language Model for Hallucination Mitigation](https://mlsanity.com/paper/2412.02790/) (2024)
- [ReqBrain: Task-Specific Instruction Tuning of LLMs for AI-Assisted Requirements Generation](https://mlsanity.com/paper/2505.17632/) (2025)
- [Exploring Causal Effect of Social Bias on Faithfulness Hallucinations in Large Language Models](https://mlsanity.com/paper/2508.07753/) (2025)
- [HAVE: Head-Adaptive Gating and ValuE Calibration for Hallucination Mitigation in Large Language Models](https://mlsanity.com/paper/2509.06596/) (2025)
- [A Concise Review of Hallucinations in LLMs and their Mitigation](https://mlsanity.com/paper/2512.02527/) (2025)
- [TrueBrief: Faithful Summarization through Small Language Models](https://mlsanity.com/paper/2601.04212/) (2025)
- [Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority](https://mlsanity.com/paper/2602.01227/) (2026)
- [Listen to the Layers: Mitigating Hallucinations with Inter-Layer Disagreement](https://mlsanity.com/paper/2602.09486/) (2026)
- [Self-Correction Inside the Model: Leveraging Layer Attention to Mitigate Hallucinations in Large Vision Language Models](https://mlsanity.com/paper/2603.00437/) (2026)
- [BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation](https://mlsanity.com/paper/2606.15893/) (2026)
- [Decomposed Entailment for Factuality Checking and Hallucination Detection](https://mlsanity.com/paper/2608.05823/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated remarkable performance on various natural language processing tasks. However, they are prone to generating fluent yet untruthful responses, known as "hallucinations". Hallucinations can lead to the spread of misinformation and cause harm in critical applications. Mitigating hallucinations is challenging as they arise from factors such as noisy data, model overconfidence, lack of knowledge, and the generation process itself. Recent efforts have attempted to address this issue through representation editing and decoding algorithms, reducing hallucinations without major structural changes or retraining. However, these approaches either implicitly edit LLMs' behavior in latent space or suppress the tendency to output unfaithful results during decoding instead of explicitly modeling on hallucination. In this work, we introduce Faithful Finetuning (F2), a novel method that explicitly models the process of faithful question answering through carefully designed loss functions during fine-tuning. We conduct extensive experiments on popular datasets and demonstrate that F2 achieves significant improvements over vanilla models and baselines.