# FLAME: Factuality-Aware Alignment for Large Language Models

arXiv: https://arxiv.org/abs/2405.01525 · HTML: https://mlsanity.com/paper/2405.01525/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 42 of its 53 references that are in the map.
- First posted on arXiv 2 May 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 30 of 42)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [Augmented Language Models: a Survey](https://mlsanity.com/paper/2302.07842/) (2023)
- [DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models](https://mlsanity.com/paper/2309.03883/) (2023)
- [A Long Way to Go: Investigating Length Correlations in RLHF](https://mlsanity.com/paper/2310.03716/) (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)
- [FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios](https://mlsanity.com/paper/2307.13528/) (2023)

## Built on by (most cited first, 30 of 47)

- [From System 1 to System 2: A Survey of Reasoning Large Language Models](https://mlsanity.com/paper/2502.17419/) (2025)
- [Know Your Limits: A Survey of Abstention in Large Language Models](https://mlsanity.com/paper/2407.18418/) (2024)
- [VERISCORE: Evaluating the factuality of verifiable claims in long-form text generation](https://mlsanity.com/paper/2406.19276/) (2024)
- [Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models](https://mlsanity.com/paper/2503.15888/) (2025)
- [Mitigating Object Hallucinations via Sentence-Level Early Intervention](https://mlsanity.com/paper/2507.12455/) (2025)
- [A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications](https://mlsanity.com/paper/2410.15595/) (2024)
- [TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning](https://mlsanity.com/paper/2509.25760/) (2025)
- [Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs](https://mlsanity.com/paper/2503.02846/) (2025)
- [A Survey on the Honesty of Large Language Models](https://mlsanity.com/paper/2409.18786/) (2024)
- [OLAPH: Improving Factuality in Biomedical Long-form Question Answering](https://mlsanity.com/paper/2405.12701/) (2024)
- [Kanana: Compute-efficient Bilingual Language Models](https://mlsanity.com/paper/2502.18934/) (2025)
- [Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models](https://mlsanity.com/paper/2502.15799/) (2025)
- [Reasoning Elicitation in Language Models via Counterfactual Feedback](https://mlsanity.com/paper/2410.03767/) (2024)
- [Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers](https://mlsanity.com/paper/2506.13342/) (2025)
- [Improving Factuality with Explicit Working Memory](https://mlsanity.com/paper/2412.18069/) (2024)
- [Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only](https://mlsanity.com/paper/2410.11055/) (2024)
- [HalluHard: A Hard Multi-Turn Hallucination Benchmark](https://mlsanity.com/paper/2602.01031/) (2026)
- [BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs](https://mlsanity.com/paper/2505.13529/) (2025)
- [ReliableMath: Benchmark of Reliable Mathematical Reasoning on Large Language Models](https://mlsanity.com/paper/2507.03133/) (2025)
- [Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration](https://mlsanity.com/paper/2410.16736/) (2024)
- [Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models](https://mlsanity.com/paper/2507.02870/) (2025)
- [MASH: Modeling Abstention via Selective Help-Seeking](https://mlsanity.com/paper/2510.01152/) (2025)
- [Self-Improving Pretraining: using post-trained models to pretrain better models](https://mlsanity.com/paper/2601.21343/) (2026)
- [Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinations](https://mlsanity.com/paper/2510.17733/) (2025)
- [Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization](https://mlsanity.com/paper/2502.19127/) (2025)
- [The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality](https://mlsanity.com/paper/2507.08371/) (2025)
- [Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality](https://mlsanity.com/paper/2509.23765/) (2025)
- [Beyond Math and Code: Lightweight Corpus-Grounded Process Rewards for Factual Question Answering](https://mlsanity.com/paper/2605.29648/) (2026)
- [3DS: Medical Domain Adaptation of LLMs via Decomposed Difficulty-based Data Selection](https://mlsanity.com/paper/2410.10901/) (2024)
- [Beyond Under-Alignment: Atomic Preference Enhanced Factuality Tuning for Large Language Models](https://mlsanity.com/paper/2406.12416/) (2024)

## Abstract (arXiv)

Alignment is a standard procedure to fine-tune pre-trained large language models (LLMs) to follow natural language instructions and serve as helpful AI assistants. We have observed, however, that the conventional alignment process fails to enhance the factual accuracy of LLMs, and often leads to the generation of more false facts (i.e. hallucination). In this paper, we study how to make the LLM alignment process more factual, by first identifying factors that lead to hallucination in both alignment steps: supervised fine-tuning (SFT) and reinforcement learning (RL). In particular, we find that training the LLM on new knowledge or unfamiliar texts can encourage hallucination. This makes SFT less factual as it trains on human labeled data that may be novel to the LLM. Furthermore, reward functions used in standard RL can also encourage hallucination, because it guides the LLM to provide more helpful responses on a diverse set of instructions, often preferring longer and more detailed responses. Based on these observations, we propose factuality-aware alignment, comprised of factuality-aware SFT and factuality-aware RL through direct preference optimization. Experiments show that our proposed factuality-aware alignment guides LLMs to output more factual responses while maintaining instruction-following capability.