arXiv:2606. 28358v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) aims to enhance the trustworthiness of Large Language Models (LLMs) by grounding their outputs in external documents, often using inline citations for verifiability.
Large language models are increasingly deployed in citation-augmented settings, yet the effect of citation presence on model behavior independent of factual content remains poorly understood. We introduce AuthorityBench, a 220,564-prompt multi-domain benchmark that isolates how citation-based authority signals influence epistemic behavior in LLMs.
arXiv:2603. 08924v2 Announce Type: replace-cross Abstract: AI-powered answer engines are inherently non-deterministic: identical queries submitted at different times can produce different responses and cite different sources.
arXiv:2608. 19230v1 Announce Type: cross Abstract: As language models move from drafting prose to running literature-search agents with tool calls, fabricated references are becoming easier to catch and constrain.
arXiv:2603. 26791v3 Announce Type: replace-cross Abstract: Assessing a cited paper's impact is typically done by analyzing its citation context in isolation within the citing paper.
arXiv:2608. 11390v1 Announce Type: new Abstract: Generative engines are reshaping the web ecosystem by making citations a key mechanism for allocating attention, attribution, and downstream value.
Retrieval-augmented generation systems for legal question answering typically retrieve passages based on semantic similarity and provide them to a language model, which then generates cited answers. Prior work assumes that highly ranked passages are most likely to be usefully cited by the model.
Reinforcement learning increasingly relies on an LLM judge to score each rubric criterion, and that judge acts as the reward model during training. Before such a signal can be trusted, we need to know how capable the judge must be and how biased it is.
The study investigates bias in large language model (LLM) judges by having ten LLMs evaluate narrative constraint selections rather than generated text. Results show that self-preference largely disappears under blind evaluation when quality and evaluator severity are controlled, but self- and other-labels alone shift scores bidirectionally when quality is matched. The authors conclude that authorship attribution drives evaluation bias and that open-ended, ground‑truth‑free tasks can effectively study LLM judge behavior.
The paper investigates whether large language models (LLMs) can reliably assess scientific hypotheses by using a logit-based energy scoring method that leverages the model’s intrinsic confidence. Across 1,323 papers in 12 disciplines, this intrinsic scoring achieved a 33.0% Hit@1 rate, outperforming a prompted listwise ranking approach that scored 16.6%. The best result, a 1‑billion‑parameter model with logit-based energy scoring, reached 53.1% Hit@1, suggesting that confidence‑based evaluation could improve trustworthy AI‑enabled scientific discovery.
Large language models (LLMs) are increasingly used for scientific hypothesis generation. However, evaluating generated hypotheses remains a challenge for trustworthy AI-enabled scientific workflows.
The paper introduces a modular data‑science pipeline that estimates public sentiment toward individuals using fragmented, unstructured open‑source intelligence. The pipeline combines web search, text extraction, relevance filtering, tokenisation, co‑reference resolution, and sentiment analysis to produce auditable person‑level sentiment distributions. By comparing AFINN, VADER, and the domain‑specific MINOS algorithm, the authors show that MINOS best distinguishes positive, ambiguous, and negative reputational cases, and they apply the method to the UK Honours system to support transparent, reproducible, human‑in‑the‑loop sentiment assessment for high‑stakes decisions.