4arXiv cs.CL (Computation and Language)·
Cost-Pragmatic Retrieval Gating and Multi-Model Fusion for BioASQ 2026 Biomedical QA
A BioASQ Task 14B 2026 system paper describes two core design decisions: a cost-pragmatic re-retrieval policy using a BGE cross-encoder quality gate, and a decomposition of multi-model ensemble lift into selection and fusion components. The retrieval pipeline unions dense (BGE + BM25 + RRF) and agent-driven PubMed/Europe PMC/iCite pipelines, achieving R@200 = 99.3% on the BioASQ-13b archive. The team places first on the combined-exact aggregate on three of eight leaderboard tracks and first on Phase B b3 ideal. GPT-5.5 solo retains list-F1 lead over a synonym-union resolver due to precision trade-offs.
Related guides (3)
Related events (8)
Question-type-aware LLM pipeline with multi-agent collaboration achieves top factoid performance on BioASQ 14b
Researchers present a question-type-specific LLM framework for the BioASQ 14b biomedical QA challenge, applying distinct inference strategies to yes/no, factoid, and list questions rather than a single unified approach. For list questions, a multi-agent architecture handles evidence extraction, candidate generation, verification, and aggregation collaboratively. The framework achieved first place in the factoid subtask of Batch 4 in the official BioASQ 14b evaluation, demonstrating competitive performance across multiple batches.
Task-specific two-agent architecture wins QANTA 2026 multimodal QA challenge
Researchers present the top-scoring submission to the QANTA 2026 shared challenge at ICML 2026's EMM-QA Workshop, achieving an overall leaderboard score of 0.402 on multimodal quizbowl tasks. The system uses a two-agent architecture: a GPT-4.1-mini-based Tossup agent with confidence calibration and a GPT-4.1-based Bonus agent with structured relational and multimodal reasoning. Notably, the approach avoids retrieval pipelines and model ensembles, relying instead on lightweight task-specific reasoning policies under efficiency constraints. Results suggest that targeted reasoning strategies can be competitive on resource-constrained multimodal QA benchmarks.
ACL-Verbatim: Hallucination-Free Extractive QA System for Research Papers
The paper introduces ACL-Verbatim, an extractive question answering system built on VerbatimRAG that maps user queries directly to verbatim text spans in ACL Anthology papers, eliminating hallucination by design. The authors contribute a new ground-truth benchmark dataset created via human NLP-researcher annotation over synthetic queries generated using a ScIRGen-based pipeline. A 150M-parameter ModernBERT token classifier trained on silver supervision achieves the best word-level F1 of 53.6, outperforming the strongest LLM-based extractor at 48.7. The work demonstrates that smaller extractive models can outperform large generative LLMs on precision-critical retrieval tasks.
KG grounding helps LLMs only for out-of-training knowledge: controlled clinical QA study
A new arXiv paper investigates when knowledge-graph (KG) grounding improves LLM performance on clinical question answering, finding that structured KG retrieval over the public biomedical graph PrimeKG provides no meaningful improvement on MedQA (all deltas ≤3.4) because the relevant facts are already in the model's training data. On synthetic counterfactual and hybrid benchmarks containing genuinely novel facts, the same pipeline lifts out-of-training accuracy from chance to ~100%. The paper also reproduces and partially corrects a recent Nature Medicine study on frontier LLMs vs. clinical RAG tools, flagging a score-deflating grader bug and clarifying that the reported ~88 HealthBench score reflects the Consensus variant, not full HealthBench (~46-47). The core finding — that RAG/KG grounding pays off only when the decisive fact is outside the model's training distribution — has direct implications for when retrieval augmentation is worth deploying.
GRASP: Plan-Guided Graph Retrieval with Adaptive Fusion and Reranking on Semi-Structured Knowledge Bases
GRASP is a three-stage retrieval framework for semi-structured knowledge bases (SKBs) that combines plan-based graph retrieval, plan-conditioned dense retrieval fusion, and a fine-tuned reranker. It targets applications like product search, academic search, and precision medicine over typed entity-relation graphs. Evaluated on the STaRK benchmarks, GRASP advances average Hit@1 from 62.0 to 73.9, representing a substantial improvement over prior hybrid retrieval systems. Ablation studies confirm the contribution of each component.
MetaSyn benchmark reveals critical screening bottleneck in LLM-based meta-analysis pipelines
Researchers introduce MetaSyn, a dataset of 442 expert-curated meta-analyses from Nature Portfolio journals, paired with a 140k-article PubMed retrieval corpus, PI/ECO criteria, verified positives, and hard negatives. Benchmarking twelve pipeline configurations — nine RAG variants and a protocol-driven agent — shows that despite 90.9% retrieval recall at K=200, no system recovers more than 52.7% of ground-truth included studies. The core failure is LLMs' inability to reliably distinguish eligible studies from topically similar but criteria-failing distractors. The paper argues that end-to-end scores obscure where pipelines break down and proposes stage-attributed metrics.
Anthropic introduces Contextual Retrieval to reduce RAG retrieval failures by up to 67%
Anthropic published a technical method called Contextual Retrieval that combines Contextual Embeddings and Contextual BM25 to address the context-loss problem in traditional RAG pipelines. The approach prepends chunk-level context before encoding, reducing failed retrievals by 49% standalone and 67% when combined with reranking. The post also highlights prompt caching as a simpler alternative for knowledge bases under 200K tokens, and provides a cookbook for deployment with Claude.
UMG-RAG: Training-free hybrid retrieval with uncertainty-aware granularity fusion for long-document RAG
Researchers propose Uncertainty-aware Multi-Granularity RAG (UMG-RAG), a training-free hybrid retrieval framework that addresses the tension between large and fine-grained retrieval chunks in RAG pipelines. The system converts dense and sparse retriever scores across multiple chunk granularities into evidence distributions, estimates reliability via entropy, and fuses candidates using query-specific confidence signals. A variant called UMGP-RAG uses fine-grained hits to locate evidence while returning broader parent chunks for coherence. Experiments on QA benchmarks show improved generation quality with no changes to the underlying retriever or generator.