# Advancing Large Language Model Attribution through Self-Improving

arXiv: https://arxiv.org/abs/2410.13298 · HTML: https://mlsanity.com/paper/2410.13298/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 18 of its 33 references that are in the map.
- First posted on arXiv 17 Oct 2024.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)
- Synthetic data and self-improvement for LLMs / [Synthetic reasoning data and bootstrapping](https://mlsanity.com/synth/synthetic-reasoning-data-and-bootstrapping/)

## Builds on (most cited first, 18 of 18)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [Reinforced Self-Training (ReST) for Language Modeling](https://mlsanity.com/paper/2308.08998/) (2023)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [Evaluating Verifiability in Generative Search Engines](https://mlsanity.com/paper/2304.09848/) (2023)
- [ASQA: Factoid Questions Meet Long-Form Answers](https://mlsanity.com/paper/2204.06092/) (2022)
- [V-STaR: Training Verifiers for Self-Taught Reasoners](https://mlsanity.com/paper/2402.06457/) (2024)
- [Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing](https://mlsanity.com/paper/2404.12253/) (2024)
- [A Survey of Large Language Models Attribution](https://mlsanity.com/paper/2311.03731/) (2023)
- [The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus](https://mlsanity.com/paper/2112.09924/) (2021)
- [Training Language Models to Generate Text with Citations via Fine-grained Rewards](https://mlsanity.com/paper/2402.04315/) (2024)
- [Genie: Achieving Human Parity in Content-Grounded Datasets Generation](https://mlsanity.com/paper/2401.14367/) (2024)
- [Improving Attributed Text Generation of Large Language Models via Preference Learning](https://mlsanity.com/paper/2403.18381/) (2024)

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

- [SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models](https://mlsanity.com/paper/2502.09604/) (2025)
- [Pre-training Limited Memory Language Models with Internal and External Knowledge](https://mlsanity.com/paper/2505.15962/) (2025)
- [Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models](https://mlsanity.com/paper/2508.18381/) (2025)
- [Tracing the Data Trail: A Survey of Data Provenance, Transparency and Traceability in LLMs](https://mlsanity.com/paper/2601.14311/) (2026)
- [Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models](https://mlsanity.com/paper/2603.13985/) (2026)
- [On Synthesizing Data for Context Attribution in Question Answering](https://mlsanity.com/paper/2504.05317/) (2025)
- [Efficient Online RFT with Plug-and-Play LLM Judges: Unlocking State-of-the-Art Performance](https://mlsanity.com/paper/2506.05748/) (2025)
- [CAGE: Cognitive Attribution Graphs for Faithful Inline Citation Generation in Long-Form Question Answering](https://mlsanity.com/paper/2607.24236/) (2026)
- [One for All: Update Parameterized Knowledge Across Multiple Models](https://mlsanity.com/paper/2506.00817/) (2025)
- [A Large Language Model Based Pipeline for Review of Systems Entity Recognition from Clinical Notes](https://mlsanity.com/paper/2506.11067/) (2025)
- [Jointly Generating and Attributing Answers using Logits of Document-Identifier Tokens](https://mlsanity.com/paper/2508.08942/) (2025)
- [FinLFQA: Evaluating Attributed Text Generation of LLMs in Financial Long-Form Question Answering](https://mlsanity.com/paper/2510.06426/) (2025)
- [C2-Cite: Contextual-Aware Citation Generation for Attributed Large Language Models](https://mlsanity.com/paper/2602.00004/) (2025)
- [Co-LMLM: Continuous-Query Limited Memory Language Models](https://mlsanity.com/paper/2607.07707/) (2026)

## Abstract (arXiv)

Teaching large language models (LLMs) to generate text with citations to evidence sources can mitigate hallucinations and enhance verifiability in information-seeking systems. However, improving this capability requires high-quality attribution data, which is costly and labor-intensive. Inspired by recent advances in self-improvement that enhance LLMs without manual annotation, we present START, a Self-Taught AttRibuTion framework for iteratively improving the attribution capability of LLMs. First, to prevent models from stagnating due to initially insufficient supervision signals, START leverages the model to self-construct synthetic training data for warming up. To further self-improve the model's attribution ability, START iteratively utilizes fine-grained preference supervision signals constructed from its sampled responses to encourage robust, comprehensive, and attributable generation. Experiments on three open-domain question-answering datasets, covering long-form QA and multi-step reasoning, demonstrate significant performance gains of 25.13% on average without relying on human annotations and more advanced models. Further analysis reveals that START excels in aggregating information across multiple sources.