The paper reports the ABAI submission to COLIEE 2026 Task 1, a case law retrieval challenge that suppresses cited passages, and details a four‑stage retrieval pipeline: multi‑view BM25 with reciprocal rank fusion, neural reranking, graph‑based features via a graph attention network, and a LightGBM meta‑learner over 34 features. The best run achieved an F1 score of 0.177 on the official test set, compared to a cross‑validated 0.311, and the authors attribute the gap to a recall ceiling, temporal distribution shift, and threshold miscalibration. A controlled post‑hoc study examined the impact of threshold transfer, decision quality across time, and query similarity, and identified specific remedies—such as BM25 length‑normalisation tuning, event‑triple views, and dense fusion—that improved recall, while other interventions had no effect.
By Minhan Cho, Soyoung Park, Daejin Choi, Jinyoung Han
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.
By Kaysarul Anas Apurba, Md. Hasibul Hasan, Rofiqul Alam Shehab, Asab Azad
arXiv:2604. 19047v2 Announce Type: replace-cross Abstract: Existing QA benchmarks typically assume distinct documents with minimal overlap, yet real-world retrieval-augmented generation (RAG) systems operate on corpora such as financial reports, legal codes, and patents, where information is highly redundant and documents exhibit strong inter-document similarity.
By Hanjun Cho, Jay-Yoon Lee
arXiv:2606. 28367v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) is routinely extended with methods meant to improve retrieval: query expansion, hierarchical and cross-document summarization, graph-based expansion, per-query routing, rank fusion, and corrective re-retrieval.
By Sadanand Singh, Allam Reddy, Manan Chopra
The paper introduces three retrieval methods for Polish statutory law that use language‑model annotations attached to articles as surrogates. The methods—ASCR, ASCR‑H, and DTF—vary in cost and quality, with ASCR‑H achieving the highest rank‑one accuracy on bar exam questions, while DTF offers competitive performance with lower latency and cost. Extensive evaluation against 14 baselines on 300 exam questions demonstrates significant improvements in head‑rank accuracy and discusses limitations such as coverage asymmetry and negative results for lemmatisation, pseudo‑relevance feedback, and query rewriting.
By Orkun Yi\u{g}it Cengiz
Re:CAP is a reference‑free audit loop for retrieval‑augmented generation (RAG) pipelines that probes for missing documents instead of enumerating all relevant ones. It identifies covered topics, generates probing questions, retrieves candidate documents, and uses an LLM judge to keep only those that add new information. On several benchmarks, Re:CAP recovers a significant portion of gold documents that flat BM25 or hybrid retrieval misses, and human evaluation shows most of these documents add new information.
By Aviral Joshi, Hanoz Bhathena, Max Nelson, Saket Sharma
arXiv:2608. 14841v1 Announce Type: new Abstract: Long-document visual question answering (VQA) over documents of tens to hundreds of pages mixing text, tables, charts, and figures typically follows retrieve-then-read pipelines.
By Guanchen Wu, Jiayuan Ding, Subhabrata Mukherjee, Carl Yang
arXiv:2609.37574v1 Announce Type: cross
Abstract: Large Language Models (LLMs) are increasingly used to enrich user queries in information retrieval (IR) so that a standard retriever such as BM25 can...
By Tzu-I Ho, Yung-Yu Shih, Shang-Yu Su, Dongzhe Wang, Yun-Nung Chen
SHELF is a Python system that creates synthetic, controlled benchmark data for evaluating large language models on bibliographic tasks such as classification, clustering, retrieval, pair classification, and instruction retrieval. It generates 62,899 model-written documents based on Library of Congress vocabularies and compares methods like TF, TF‑IDF, BM25, popular encoders, and zero‑shot decoders, reporting performance metrics such as 0.8887 for subject classification and 0.2605 for genre‑form classification. The tool also allows independent variation of bibliographic facets and can produce unseen documents beyond a model’s training cutoff, with results indicating that model rankings transfer more reliably than absolute scores when compared to other benchmarks.
By Michael J. Bommarito II
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.
By Bhagyesh Rathi, Eshan Chawla, William B. Andreopoulos
Hybrid Retrieval-Augmented Generation with Knowledge Graph Expansion, RRF Fusion, and Per-Chunk Grounded Evaluation for Enterprise Document Search describes DocuSearch, an offline multi‑agent system designed for telecom network operations. The system combines semantic vector search, BM25 full‑text search, and knowledge‑graph neighbor expansion, merges the results via Reciprocal Rank Fusion, and reranks with a cross‑encoder before pruning with Maximal Marginal Relevance. A per‑chunk evaluation loop ensures only grounded answers are returned, achieving Precision@10 of 0.69, Recall@10 of 0.79, and an 89.6% grounding rate—improvements of 15, 16, and 18.4 percentage points over a dense‑only baseline.
By Harish Saragadam, Sudhanshu Sharma, Meghana Pujari
arXiv:2607. 16848v1 Announce Type: cross Abstract: Long-term memory is becoming a core component of LLM agents, but most memory benchmarks evaluate conversations or compact summaries, while research agents need to restore evidence from full scientific papers.
By Maksim Sheverev, David Finkelstein, Sergey Nikolenko