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.
Related guides (3)
Related events (8)
Act2Answer: Benchmarking commonsense and world knowledge retention in Vision-Language-Action models
Researchers introduce Act2Answer, a protocol for evaluating how much commonsense and factual knowledge VLA models retain after fine-tuning on robotics data. The approach converts knowledge benchmark questions into tabletop object-placement episodes, yielding action-grounded success rates that reduce confounds from low-level control failures. A large-scale study of 7 VLA models and 9 VLM baselines finds that VLAs retain solid performance on simple concepts but show larger gaps on richer semantic categories compared to their source VLMs, and that VQA co-training is associated with better knowledge retention.
SPECTRA: Synthetic IR Test Collections with Relevance Oracles and Controlled Distractor Diagnostics
SPECTRA is a reproducible framework for generating synthetic information retrieval test collections, separating latent topical structure, surface text realization, and query intent generation to produce deterministic relevance oracles without human annotation. A Python prototype generated corpora up to 60,000 documents at roughly 12K–14K documents per second, with graded relevance labels for 96 queries. Controlled distractor experiments showed BM25 nDCG@10 degrading from 1.00 at 2% distractors to 0.43 at 36%, demonstrating the framework's utility for exposing retrieval system failure modes before expensive real-world collection construction. The authors position SPECTRA as a diagnostic complement to Cranfield/TREC-style evaluation rather than a replacement for human judgment.
WikiVQABench: A Knowledge-Grounded Visual Question Answering Benchmark from Wikipedia and Wikidata
WikiVQABench is a new human-curated VQA benchmark that requires external knowledge beyond visual perception, constructed by combining Wikipedia images, captions, and Wikidata structured knowledge with LLM-generated question candidates reviewed by human annotators. The benchmark evaluates knowledge-intensive reasoning in vision-language models, covering 15 VLMs ranging from 256M to 90B parameters. Accuracy spans 24.7% to 75.6%, indicating meaningful discrimination across model scales. The dataset and code are publicly released.
LegalHalluLens: Typed hallucination auditing and calibrated multi-agent debate for legal AI
Researchers introduce LegalHalluLens, an auditing framework for hallucination in legal AI systems, evaluated across 510 contracts and 249,252 clause-level instances from the CUAD dataset. The framework introduces typed hallucination profiles across four claim categories (numeric, temporal, obligation/entitlement, factual) and a Risk Direction Index (RDI) that distinguishes omission from invention errors. A calibrated multi-agent debate pipeline reduces fabricated detections by 45% using a 4B-parameter model competitive with commercial APIs. The work reveals that aggregate hallucination rates (~52%) mask a 38-40 percentage-point gap between claim types and that two systems with identical aggregate rates can have opposite risk profiles.
DocTrace: Structure-Aware On-Demand Hypergraph Memory for Long-Document QA
Researchers introduce DocTrace, a multi-agent RAG framework for long-document question answering that uses query-triggered knowledge organization rather than costly query-agnostic preprocessing. The system combines a lightweight document structural tree index, on-demand hypergraph working memory, and a graph-structured experience memory that stores successful reasoning plans for reuse. Evaluated on four long-document QA datasets, DocTrace outperforms the strongest baseline (ComoRAG) by up to 8.85% F1 and 4.40% EM while reducing computational cost by 53.32%.
ParaEval framework reduces MCQA benchmark sensitivity to answer phrasing
A new arXiv preprint identifies a systematic flaw in multiple-choice QA benchmarks: log-likelihood scoring conflates surface-form familiarity with actual capability, producing false performance gaps exceeding 2 points between models trained on identical knowledge. The authors propose ParaEval, which queries models with multiple paraphrases per answer option and scores on the most favorable phrasing, reducing the false gap to below 1 point. The effect is confirmed on frontier 70B and 120B open-source models, suggesting widespread benchmark inflation in standard MCQA evaluations.
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.
AgentCL: A Rigorous Evaluation Framework for Continual Learning in Language Agents
AgentCL is a new benchmark and evaluation framework designed to rigorously assess continual learning in language agents, addressing gaps in existing benchmarks that focus on retrieval over long-context documents or use naive task streams with limited cross-task analysis. The framework constructs compositional task streams where earlier sub-solutions, evidence, or workflows are intentionally reusable in later tasks, contrasting them with naive streams to measure transfer gains. The authors also introduce MemProbe, a probing method that stores interactions, insights, and skills while filtering unreliable experiences during consolidation. Empirical results across coding, deep research, and language understanding tasks show that controlled streams better distinguish memory design quality, and that naive streams can mask memory-induced degradation.