# Fine-tuning Large Language Models for Improving Factuality in Legal Question Answering

arXiv: https://arxiv.org/abs/2501.06521 · HTML: https://mlsanity.com/paper/2501.06521/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 55 references that are in the map.
- First posted on arXiv 11 Jan 2025.

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

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [ORPO: Monolithic Preference Optimization without Reference Model](https://mlsanity.com/paper/2403.07691/) (2024)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [Fine-tuning Language Models for Factuality](https://mlsanity.com/paper/2311.08401/) (2023)
- [Factuality Enhanced Language Models for Open-Ended Text Generation](https://mlsanity.com/paper/2206.04624/) (2022)
- [When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset](https://mlsanity.com/paper/2104.08671/) (2021)
- [CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction](https://mlsanity.com/paper/1807.02478/) (2018)
- [A Survey of Large Language Models in Medicine: Progress, Application, and Challenge](https://mlsanity.com/paper/2311.05112/) (2023)
- [Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss](https://mlsanity.com/paper/2312.16682/) (2023)
- [Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback](https://mlsanity.com/paper/2404.14233/) (2024)
- [Can GPT-3 Perform Statutory Reasoning?](https://mlsanity.com/paper/2302.06100/) (2023)
- [FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets](https://mlsanity.com/paper/2310.04793/) (2023)
- [Legal Prompt Engineering for Multilingual Legal Judgement Prediction](https://mlsanity.com/paper/2212.02199/) (2022)
- [Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks](https://mlsanity.com/paper/2404.14723/) (2024)
- [Exploiting Contrastive Learning and Numerical Evidence for Confusing Legal Judgment Prediction](https://mlsanity.com/paper/2211.08238/) (2022)
- [Enhancing Court View Generation with Knowledge Injection and Guidance](https://mlsanity.com/paper/2403.04366/) (2024)
- [Dialogue Inspectional Summarization with Factual Inconsistency Awareness](https://mlsanity.com/paper/2111.03284/) (2021)
- [From Graph to Word Bag: Introducing Domain Knowledge to Confusing Charge Prediction](https://mlsanity.com/paper/2403.04369/) (2024)

## Built on by (most cited first, 28 of 28)

- [A Survey of Direct Preference Optimization](https://mlsanity.com/paper/2503.11701/) (2025)
- [Towards Robust Legal Reasoning: Harnessing Logical LLMs in Law](https://mlsanity.com/paper/2502.17638/) (2025)
- [Explainable Rule Application via Structured Prompting: A Neural-Symbolic Approach](https://mlsanity.com/paper/2506.16335/) (2025)
- [Evaluating Test-Time Scaling LLMs for Legal Reasoning: OpenAI o1, DeepSeek-R1, and Beyond](https://mlsanity.com/paper/2503.16040/) (2025)
- [LRAS: Advanced Legal Reasoning with Agentic Search](https://mlsanity.com/paper/2601.07296/) (2026)
- [Challenges for Generative AI in Legal Reasoning](https://mlsanity.com/paper/2508.18880/) (2025)
- [WaterMod: Modular Token-Rank Partitioning for Probability-Balanced LLM Watermarking](https://mlsanity.com/paper/2511.07863/) (2025)
- [LLM Abstention Can Be a Prompt Artifact, in Addition to Genuine Uncertainty](https://mlsanity.com/paper/2507.16199/) (2025)
- [Distributional Semantics Tracing: A Framework for Explaining Hallucinations in Large Language Models](https://mlsanity.com/paper/2510.06107/) (2025)
- [A Linguistics-Aware LLM Watermarking via Syntactic Predictability](https://mlsanity.com/paper/2510.13829/) (2025)
- [Building from Scratch: A Multi-Agent Framework with Human-in-the-Loop for Multilingual Legal Terminology Mapping](https://mlsanity.com/paper/2512.12950/) (2025)
- [Domain-Adaptation through Synthetic Data: Fine-Tuning Large Language Models for German Law](https://mlsanity.com/paper/2601.14160/) (2026)
- [Who Checks the Citations? Benchmarking Legal Hallucination Detection](https://mlsanity.com/paper/2606.21155/) (2026)
- [KnowHal: A Knowledge-Driven Benchmark for Comprehensive Multimodal Hallucination Evaluation](https://mlsanity.com/paper/2608.03782/) (2026)
- [Legal LLM Hallucination Should Be Evaluated as Failure of Legal Warrant](https://mlsanity.com/paper/2609.17546/) (2026)
- [Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge](https://mlsanity.com/paper/2505.16178/) (2025)
- [CrunchLLM: Multitask LLMs for Structured Business Reasoning and Outcome Prediction](https://mlsanity.com/paper/2509.10698/) (2025)
- [Structured Decomposition for LLM Reasoning: Cross-Domain Validation and Semantic Web Integration](https://mlsanity.com/paper/2601.01609/) (2026)
- [AdversaRiskQA: An Adversarial Factuality Benchmark for High-Risk Domains](https://mlsanity.com/paper/2601.15511/) (2026)
- [CaseFacts: A Benchmark for Legal Fact-Checking and Precedent Retrieval](https://mlsanity.com/paper/2601.17230/) (2026)
- [Be My Tutor: On-Policy Co-Distillation for Mutual LLM Improvement via Peer Feedback](https://mlsanity.com/paper/2606.14368/) (2026)
- [InsufficiencyBench: Evaluating LLM legal advice on underspecified user queries](https://mlsanity.com/paper/2608.20220/) (2026)
- [From Atoms to Chains: Divergence-Guided Reasoning Curriculum for Unlabeled LLM Domain Adaptation](https://mlsanity.com/paper/2601.19588/) (2026)
- [Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority](https://mlsanity.com/paper/2602.01227/) (2026)
- [Enhancing Legal LLMs through Metadata-Enriched RAG Pipelines and Direct Preference Optimization](https://mlsanity.com/paper/2603.19251/) (2026)
- [PoliLegalLM: A Technical Report on a Large Language Model for Political and Legal Affairs](https://mlsanity.com/paper/2604.17543/) (2026)
- [How Much Do Legal RAG Systems Still Hallucinate?](https://mlsanity.com/paper/2608.14210/) (2026)
- [LexAgentHallu: A Hierarchical Benchmark for Profiling Hallucinations in Legal Agents](https://mlsanity.com/paper/2609.09754/) (2026)

## Abstract (arXiv)

Hallucination, or the generation of incorrect or fabricated information, remains a critical challenge in large language models (LLMs), particularly in high-stake domains such as legal question answering (QA). In order to mitigate the hallucination rate in legal QA, we first introduce a benchmark called LegalHalBench and three automatic metrics to evaluate the common hallucinations when LLMs answer legal questions. We then propose a hallucination mitigation method that integrates behavior cloning and a novel Hard Sample-aware Iterative Direct Preference Optimization (HIPO). We conduct extensive real-data experiments to validate the effectiveness of our approach. Our results demonstrate remarkable improvements in various metrics, including the newly proposed Non-Hallucinated Statute Rate, Statute Relevance Rate, Legal Claim Truthfulness, as well as traditional metrics such as METEOR, BERTScore, ROUGE-L, and win rates.