ResearchHub is an interactive system designed for personalized discovery of biomedical preprints. It uses a bi‑encoder retriever called prism, which leverages GPT‑4o‑generated queries and a hybrid ranking objective, to retrieve relevant papers from a MedRxiv corpus. The system enhances recommendation quality through novelty, diversity, curriculum ordering, and provides frontier retrieval, DPP‑based re‑ranking, and lightweight attribution cards, all operating with low latency.
arXiv:2608. 03860v1 Announce Type: cross Abstract: We introduce SciRet, a compute-aware empirical study of retrieval-augmented generation for scientific question answering over CORD-19.
The paper presents a new retrieval benchmark for the model organism Dictyostelium, created from curator-generated queries linked to PubMed articles and gene annotations. It evaluates three niche retrieval strategies—cross‑encoder reranking, gene‑aware query expansion, and abstract‑only versus full‑text retrieval—finding that reranking and gene‑aware expansion improve results in specific contexts, while full‑text chunks boost recall and top‑rank performance when abstracts lack supporting evidence. The benchmark, data, and code are publicly released on GitHub and Zenodo.
Lit3R is a system developed by tus-nlp for the LitTraceQA shared task, which focuses on evidence-grounded question answering over scientific literature. The system combines off-the-shelf retrieval, reranking, and large language model components without task-specific training, using an iterative retrieval process that merges BM25-based sparse and dense retrieval, cross-encoder reranking, and LLM verification, along with paper-to-paper expansion. In the official test set, Lit3R achieved a 4th place ranking on the leaderboard.
arXiv:2608. 04144v1 Announce Type: cross Abstract: Biomedical entity linking grounds mentions in clinical and scientific text to entities in a curated knowledge base (KB) with ontological structure, which supports downstream applications such as literature-scale information extraction and patient-record normalization.
BioELX is a retrieve‑rerank framework for cross‑lingual biomedical entity linking that tackles two key problems: the English‑biased UMLS alias training data and the degradation caused by naïvely adding context. It fine‑tunes SapBERT_multi with Wikidata‑derived cross‑lingual alias supervision to create shared concept neighborhoods, and then reranks candidates using pretrained LLMs with mention‑anchored prompting to focus on the target mention. Experiments demonstrate state‑of‑the‑art performance on four benchmarks, improving Recall@1 by 4.8–18.2 percentage points without task‑specific annotations.
BELXTR is a new biomedical entity linking model that uses a multi‑vector (late interaction) architecture to preserve token‑level matching information, unlike traditional embedding‑based approaches that compress mentions into a single vector. By extending the XTR model with a task‑specific training objective and active query expansion, BELXTR achieves state‑of‑the‑art performance on half of ten evaluated corpora, with an average 5‑percentage‑point gain in recall@1. The model shows especially strong results on cross‑species gene disambiguation, outperforming an LLM‑powered retrieve‑and‑rerank pipeline and approaching a specialized rule‑based system.
arXiv:2607. 04088v1 Announce Type: cross Abstract: LongEval-Sci evaluates scientific retrieval under collection change, where a system should be effective on the current corpus and remain usable as documents accumulate over time.
arXiv:2609.08174v1 Announce Type: new Abstract: We introduce OntologyBench, a tiered biomedical retrieval benchmark comprising 471,854 training and 125,744 evaluation query-document relevance pairs a...
The study evaluates six retrieval methods for ranking computer science faculty as potential academic advisors based on graduate applicants’ research interest statements. Using a new dataset of 768 faculty profiles from nine U.S. universities and 162 graded relevance judgments across five queries, the reranked hybrid approach achieved the highest mean NDCG@10 (0.477). Ablation experiments showed that faculty biographies alone outperform the full model, and adding arXiv abstracts actually decreased performance, leading to a late‑fusion design. All code, data, and labels are publicly released.
RATIO (Retrieval Across Typed Ideation Operations) is a large-scale benchmark designed to evaluate how well retrieval systems can support scientific inspiration. It defines relevance through three ideation moves—Address, Broaden, and Specify—each targeting different levels of abstraction in literature retrieval. The benchmark is built from millions of full-text CS papers using a novel discourse-marker distant supervision method, and includes extensive LLM and human vetting to ensure quality.
The paper presents a controlled comparison of six retrieval-augmented generation (RAG) strategies for scientific question answering on a large arXiv corpus. All pipelines use the same LLM generator and evaluation protocol, differing only in retrieval design—ranging from classic dense retrieval to late‑interaction methods like ColBERTv2. The authors also release a synthetic question dataset and code to enable reproducible, large‑scale evaluation of RAG trade‑offs.
The paper introduces ORDER, a task‑conditioned retrieval‑augmented generation framework that dynamically adapts both indexing and retrieval strategies to each incoming query. It first clusters questions to learn cluster‑specific chunking, metadata filtering, and reranking settings, then routes queries to the appropriate pre‑built index via nearest‑centroid assignment. Additionally, a supervised query router predicts relevant collections and a Uniform Multi‑source Sampler distributes the retrieval budget evenly across selected sources, yielding superior performance on heterogeneous historical archives compared to existing RAG systems.