# SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models

arXiv: https://arxiv.org/abs/2502.09604 · HTML: https://mlsanity.com/paper/2502.09604/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Preference alignment for recommenders and RAG, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 36 of its 44 references that are in the map.
- First posted on arXiv 13 Feb 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Preference alignment for recommenders and RAG](https://mlsanity.com/alignment/preference-alignment-for-recommenders-and-rag/)

## Builds on (most cited first, 30 of 36)

- [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)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Efficient Attentions for Long Document Summarization](https://mlsanity.com/paper/2104.02112/) (2021)
- [Trusting Your Evidence: Hallucinate Less with Context-aware Decoding](https://mlsanity.com/paper/2305.14739/) (2023)
- [Teaching language models to support answers with verified quotes](https://mlsanity.com/paper/2203.11147/) (2022)
- [RARR: Researching and Revising What Language Models Say, Using Language Models](https://mlsanity.com/paper/2210.08726/) (2022)
- [Rationalizing Neural Predictions](https://mlsanity.com/paper/1606.04155/) (2016)
- [Iterative Reasoning Preference Optimization](https://mlsanity.com/paper/2404.19733/) (2024)
- [Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps](https://mlsanity.com/paper/2407.07071/) (2024)
- [Controlled Decoding from Language Models](https://mlsanity.com/paper/2310.17022/) (2023)
- [Liger Kernel: Efficient Triton Kernels for LLM Training](https://mlsanity.com/paper/2410.10989/) (2024)
- [DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications](https://mlsanity.com/paper/1711.05073/) (2017)
- [LongAlign: A Recipe for Long Context Alignment of Large Language Models](https://mlsanity.com/paper/2401.18058/) (2024)
- [ContextCite: Attributing Model Generation to Context](https://mlsanity.com/paper/2409.00729/) (2024)
- [LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA](https://mlsanity.com/paper/2409.02897/) (2024)
- [Aligning Large Language Models through Synthetic Feedback](https://mlsanity.com/paper/2305.13735/) (2023)

## Built on by (most cited first, 20 of 20)

- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [Search Arena: Analyzing Search-Augmented LLMs](https://mlsanity.com/paper/2506.05334/) (2025)
- [LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts](https://mlsanity.com/paper/2510.19363/) (2025)
- [Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.16415/) (2025)
- [Generation-Time vs. Post-hoc Citation: A Holistic Evaluation of LLM Attribution](https://mlsanity.com/paper/2509.21557/) (2025)
- [MedPAIR: Measuring Physicians and AI Relevance Alignment in Medical Question Answering](https://mlsanity.com/paper/2505.24040/) (2025)
- [Influential Training Data Retrieval for Explaining Verbalized Confidence of LLMs](https://mlsanity.com/paper/2601.10645/) (2026)
- [MaxShapley: Towards Incentive-compatible Generative Search with Fair Context Attribution](https://mlsanity.com/paper/2512.05958/) (2025)
- [Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models](https://mlsanity.com/paper/2506.17585/) (2025)
- [TrustRAG: An Information Assistant with Retrieval Augmented Generation](https://mlsanity.com/paper/2502.13719/) (2025)
- [DePass: Unified Feature Attributing by Simple Decomposed Forward Pass](https://mlsanity.com/paper/2510.18462/) (2025)
- [Short-Context Dominance: How Much Local Context Natural Language Actually Needs?](https://mlsanity.com/paper/2512.08082/) (2025)
- [Beyond Factual Accuracy: Evaluating Global Reasoning Integrity in RAG Systems with LogicScore](https://mlsanity.com/paper/2601.15050/) (2026)
- [ProvenAI: Provenance-Native Traces of Evidence in Generated Answers](https://mlsanity.com/paper/2606.26449/) (2026)
- [Evaluation Framework for Highlight Explanations of Context Utilisation in Language Models](https://mlsanity.com/paper/2510.02629/) (2025)
- [MMLongCite: A Benchmark for Evaluating Fidelity of Long-Context Vision-Language Models](https://mlsanity.com/paper/2510.13276/) (2025)
- [Citation Failure: Definition, Analysis and Efficient Mitigation](https://mlsanity.com/paper/2510.20303/) (2025)
- [TRUE: A Trustworthy Unified Explanation Framework for Large Language Model Reasoning](https://mlsanity.com/paper/2602.18905/) (2026)
- [Tell Me Why: Designing an Explainable LLM-based Dialogue System for Student Problem Behavior Diagnosis](https://mlsanity.com/paper/2604.22237/) (2026)
- [Benchmarking and Training Reward Models for Cross-Source Evidence Grounding in Search Agents](https://mlsanity.com/paper/2610.17827/) (2026)

## Abstract (arXiv)

We introduce SelfCite, a novel self-supervised approach that aligns LLMs to generate high-quality, fine-grained, sentence-level citations for the statements in their generated responses. Instead of only relying on costly and labor-intensive annotations, SelfCite leverages a reward signal provided by the LLM itself through context ablation: If a citation is necessary, removing the cited text from the context should prevent the same response; if sufficient, retaining the cited text alone should preserve the same response. This reward can guide the inference-time best-of-N sampling strategy to improve citation quality significantly, as well as be used in preference optimization to directly fine-tune the models for generating better citations. The effectiveness of SelfCite is demonstrated by increasing citation F1 up to 5.3 points on the LongBench-Cite benchmark across five long-form question answering tasks. The source code is available at https://github.com/facebookresearch/SelfCite