Local Citation Recommendation Without Graph Signals

Benjamin Basseri; Pavlos Protopapas; Kemeng Zhang; Alberto Accomazzi; Stephanie Jarmak; Anna Kelbert

cs.IROct 11, 2026

Local Citation Recommendation Without Graph Signals

Authors: Benjamin Basseri, Pavlos Protopapas, Kemeng Zhang, Alberto Accomazzi, Stephanie Jarmak, Anna Kelbert

Organizations: Harvard University · Center for Astrophysics | Harvard & Smithsonian

Abstract

Resolving correct citations can be a time-consuming task for research writers. We address local citation recommendation (LCR), where the goal is to retrieve appropriate references for a given sentence. Web tools generally depend on the existing citation graph, which may bias results toward citation count or more recent publications. LCR research using full paper texts has been limited by the lack of publicly available data. We present a new dataset, the Local Citation Recommendation Corpus (LCRC), containing 14,735 scientific statements derived from astrophysics review papers, each with one or more citation targets whose full text is accessible via API. Using this dataset we systematically compare retrieval methods and develop a citation recommendation system that avoids citation graph bias while achieving 8.0% improvement in Recall@25 and 6.9% improvement in NDCG@25 over dense retrieval baselines without model fine-tuning. To support reproducibility, we make our code and dataset publicly available.

Figures & tables

Panel of Figure 1 — Figure 1: Query dataset construction pipeline. An automated pipeline processes 3,000 ADS review papers. Sentences are split, then an LLM agent filters out captions, reference entries, and OCR errors. Inline citations are extracted as (Author, Year) tuples and resolved to DOIs via the paper’s bibliography; any sentence with an unresolved citation is dropped, yielding 14,735 labeled query samples.

	Hitrate			Recall			NDCG
Embedder	@10	@25	@50	@10	@25	@50	@10	@25	@50
astroBERT	0.1002	0.1621	0.2256	0.0829	0.1372	0.1946	0.0472	0.0613	0.0731
astrollama	0.3221	0.4347	0.5292	0.2844	0.3938	0.4847	0.1881	0.2163	0.2349
AstroSage-8B	0.1898	0.2611	0.3237	0.1622	0.2282	0.2873	0.1068	0.1240	0.1361
bge-large-en-v1.5	0.5623	0.6617	0.7255	0.5126	0.6160	0.6844	0.3868	0.4139	0.4281
nasa-ibm-st.38m	0.5241	0.6269	0.7020	0.4761	0.5796	0.6585	0.3560	0.3832	0.3996

Table 1: Embedding Model Comparison. Hitrate, Recall and NDCG at ranks 10, 25, and 50 for evaluated embedders. General-purpose embedding models Qwen3-Embedding-8B and bge-large-en-v1.5 consistently outperform astrophysics fine-tuned LLMs.

Figure 2: Comparison of document representation strategies. Baseline chunking outperformed LLM-extracted contributions (v1: simple prompt; v2: engineered prompt). Hitrate@ $k$ and NDCG@ $k$ showed similar trends.

	Hitrate			Recall			NDCG
Method	@10	@25	@50	@10	@25	@50	@10	@25	@50
Identity	0.6640	0.7570	0.8126	0.6098	0.7119	0.7757	0.4801	0.5072	0.5206
Add-Title	0.6546	0.7562	0.8225	0.6012	0.7107	0.7862	0.4647	0.4936	0.5094
Add-Abstract	0.4422	0.5798	0.6807	0.3991	0.5350	0.6387	0.2725	0.3077	0.3291
Add-Title+Prev-3	0.6085	0.7268	0.8012	0.5578	0.6812	0.7620	0.4091	0.4415	0.4584
Add-Prev-3	0.5944	0.7169	0.7953	0.5442	0.6707	0.7554	0.3984	0.4317	0.4493

Table 2: Query Expansion Comparison. Hitrate, recall, and NDCG using Qwen3-Embedding-8B and various query expansion methods.

Panel of Figure 3 — Figure 3: Grid search results for reciprocal rank fusion on original ranks from Add-Prev-02 with Log_Citations and Recency . The top-scoring weights at best matched the original ranking from Add-Prev-02 for most values of $k$ . Applying higher weights to Log_Citations and Recency tended to reduce hitrate and recall.

Information Retrieval

Information Retrieval studies how to find, rank, and organize relevant information in large collections of data.

See all 459 papers

Public Profile Matters: A Scalable Integrated Approach to Recommend Citations in the Wild
Mar 18, 2026Karan Goyal, Dikshant Kukreja, Vikram Goyal +1Recommender Systems Learning to Rank
Indraprastha Institute of Information Technology Delhi (IIIT-Delhi), New Delhi, India.
RenoBench: A Citation Parsing Benchmark
Mar 26, 2026Parth Sarin, Juan Pablo Alperin, Adam Buttrick +1Document Parsing Benchmarks Document Information Extraction
Graduate School of Education, Stanford University, Stanford, California, USA · Public Knowledge Project, Simon Fraser University, Vancouver, British Columbia, Canada · California Digital Library, University of California Office of the President, Oakland, California, USA +1
GRAFT: Graph-Distilled Generative Retrieval for Facet-Aware Scientific Literature Exploration
Aug 23, 2026Italo Luis da Silva, Hanqi Yan, Yujing Wang +3Information Retrieval Generative Retrieval
Department of Informatics King’s College London London, England, UK

Mar 18, 2026J/K move · Enter open · S save

Public Profile Matters: A Scalable Integrated Approach to Recommend Citations in the Wild

Karan Goyal, Dikshant Kukreja, Vikram Goyal, Mukesh Mohania

Indraprastha Institute of Information Technology Delhi (IIIT-Delhi), New Delhi, India.

Recommender Systems Learning to Rank IR Evaluation

Open paper AskPDF arXiv

Proper citation of relevant literature is essential for contextualising and validating scientific contributions. While current citation recommendation systems leverage local and global textual information, they often overlook the nuances of the human citation behaviour. Recent methods that incorporate such patterns improve performance but incur high computational costs and introduce systematic biases into downstream rerankers. To address this, we propose Profiler, a lightweight, non-learnable module that captures human citation patterns efficiently and without bias, significantly enhancing candidate retrieval. Furthermore, we identify a critical limitation in current evaluation protocol: the systems are assessed in a transductive setting, which fails to reflect real-world scenarios. We introduce a rigorous Inductive evaluation setting that enforces strict temporal constraints, simulating the recommendation of citations for newly authored papers in the wild. Finally, we present DAVINCI, a novel reranking model that integrates profiler-derived confidence priors with semantic information via an adaptive vector-gating mechanism. Our system achieves new state-of-the-art results across multiple benchmark datasets, demonstrating superior efficiency and generalisability.

Abstract

Information Retrieval

Explore similar work

Public Profile Matters: A Scalable Integrated Approach to Recommend Citations in the Wild

RenoBench: A Citation Parsing Benchmark

GRAFT: Graph-Distilled Generative Retrieval for Facet-Aware Scientific Literature Exploration