# ATTRICITE: Training an Open 4B Model for Citation Recovery toward Faithful Attribution

arXiv: https://arxiv.org/abs/2609.14248 · HTML: https://mlsanity.com/paper/2609.14248/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 13 Sep 2026.

## Builds on (most cited first, 24 of 24)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025)
- [Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models](https://mlsanity.com/paper/2402.14207/) (2024)
- [Mapping the Increasing Use of LLMs in Scientific Papers](https://mlsanity.com/paper/2404.01268/) (2024)
- [SciFact-Open: Towards open-domain scientific claim verification](https://mlsanity.com/paper/2210.13777/) (2022)
- [Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings](https://mlsanity.com/paper/2202.06671/) (2022)
- [Growth rates of modern science: A bibliometric analysis based on the number of publications and cited references](https://mlsanity.com/paper/1402.4578/) (2014)
- [CiteME: Can Language Models Accurately Cite Scientific Claims?](https://mlsanity.com/paper/2407.12861/) (2024)
- [Content-Based Citation Recommendation](https://mlsanity.com/paper/1802.08301/) (2018)
- [Scientific production in the era of Large Language Models](https://mlsanity.com/paper/2601.13187/) (2026)
- [HalluCitation Matters: Revealing the Impact of Hallucinated References with 300 Hallucinated Papers in ACL Conferences](https://mlsanity.com/paper/2601.18724/) (2026)
- [CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era](https://mlsanity.com/paper/2602.23452/) (2026)
- [Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents](https://mlsanity.com/paper/2605.06635/) (2026)
- [CiteGuard: Faithful Citation Attribution for LLMs via Retrieval-Augmented Validation](https://mlsanity.com/paper/2510.17853/) (2025)
- [CiteBART: Learning to Generate Citations for Local Citation Recommendation](https://mlsanity.com/paper/2412.17534/) (2024)
- [What Should I Cite? A RAG Benchmark for Academic Citation Prediction](https://mlsanity.com/paper/2601.14949/) (2026)
- [ILCiteR: Evidence-grounded Interpretable Local Citation Recommendation](https://mlsanity.com/paper/2403.08737/) (2024)

## Abstract (arXiv)

Faithful citation attribution begins with identifying the intended source for a scientific claim. We study this source-identification capability through citation recovery: recovering the paper cited by the original author from a citation-bearing passage. Our evaluation adopts the published author's citation as an observable human attribution signal and uses target recovery as a proxy for progress toward faithful attribution. We introduce ATTRICITE, an open 4B-parameter model trained for tool-using citation recovery within the CiteGuard retrieval environment, together with CITEALIGN, a 7,607-instance computer-science dataset drawn from recent scientific literature. For controlled evaluation, we construct a 709-instance benchmark subset of CITEALIGN, comprising 410 development instances from 2024 publications and 299 temporally held-out test instances from 2025 publications. Across three runs at an inference temperature of 0.7, GRPO fine-tuning improves Qwen3-4B from 49.4%±1.5% to 59.8%±0.2% target-match accuracy, a gain of 10.4 percentage points. Despite using only 4B parameters, ATTRICITE outperforms gpt-oss-20b and comes within 3.9 points of GPT-5.4-mini, while Gemma 4 31B IT achieves the strongest overall performance at 72.0%±1.0%. We release the model and collection pipeline https://github.com/KathCYM/AttriCite to support reproducible research on citation recovery toward faithful attribution in a continually evolving scientific literature.