REPAIR is a self‑evolving data augmentation framework designed to improve scientific dense retrievers by addressing long‑tail concept gaps and fact sensitivity. It iteratively generates training data through diagnosis of long‑tail concepts, API‑guided evidence expansion, and hard negative mining, thereby grounding retrieval in factual reality. Experiments show that REPAIR outperforms 19 strong baselines across nine materials science and biomedical benchmarks.
Precise retrieval of scientific information is fundamentally constrained by long-tailed concepts and high fact-sensitivity of scientific corpora. These challenges often limit the effectiveness of dens...
The paper introduces the task of Scientific Claim Unlearning and presents a new benchmark, SciUnlearn, to evaluate it. It highlights that language models trained on static scientific corpora risk disseminating outdated or retracted claims as scientific knowledge evolves. Current machine unlearning methods fail to effectively remove claim-level knowledge, often only suppressing it superficially, underscoring the need for specialized techniques for structured knowledge removal.
arXiv:2607. 20926v1 Announce Type: new Abstract: Scientific research involves complex information-seeking and reasoning workflows across heterogeneous sources.
The paper investigates why retrieval‑based open‑ended evaluation fails in medical fact verification. By creating two detailed taxonomies—one for retrieval‑stage errors across five quality dimensions and another for verifier‑reasoning errors across six steps—the authors automatically label evidence quality and reasoning errors using an LLM‑as‑Judge pipeline. Their large‑scale stress tests across multiple retrieval methods and verifier models show that increasing model size, reasoning effort, source breadth, or medical fine‑tuning does not eliminate these failure modes, indicating fundamental limits of the retrieve‑then‑verify paradigm in open‑ended medical contexts.
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 introduces VERA-RL, a reinforcement‑learning framework for proactive scientific error verification in academic papers. It builds on a Reason–Verify–Scan workflow and presents VERA‑13K, a 12,900‑sample dataset with 4,300 matched reasoning chains covering six error categories across natural‑science domains. The authors also define fine‑grained rewards for reasoning completeness, evidence alignment, and error precision, and show that training Qwen3‑VL‑8B with VERA‑RL improves verifiable reasoning to levels comparable with flagship multimodal large language models.
arXiv:2607. 01131v1 Announce Type: cross Abstract: Autonomous scientific discovery systems offer the potential to accelerate research by automating the process of hypothesis generation and validation.
arXiv:2603. 03322v2 Announce Type: replace-cross Abstract: Recent advancements in Large Language Model (LLM) agents have demonstrated remarkable potential in automatic knowledge discovery.
arXiv:2606.21359v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to communicate and explain scientific concepts, yet their tendency to hallucinate poses signific...
arXiv:2604. 13201v2 Announce Type: replace-cross Abstract: Large language models are emerging as scientific assistants, but evaluating their ability to reason from empirical data remains challenging.
arXiv:2608.29604v1 Announce Type: cross Abstract: Vision-language retrieval with CLIP-style dual encoders achieves strong cross-modal performance, yet practical accuracy often hinges on localized sem...
The article examines how scientific literature, often used as a data source for AI in materials science, can contain hidden inaccuracies such as text-figure mismatches, ambiguous axis labels, unit inconsistencies, and missing measurement context. By tracing solid electrolyte conductivity values from original papers to curated datasets, the authors uncover recurrent errors that are numerically plausible yet hard to detect, leading to significant label noise in AI models. A cross-database example demonstrates that ambiguous reporting can cause a 100‑fold error in conductivity values, underscoring the need for traceable reporting, rigorous curation, and validation practices in AI-driven discovery.