arXiv:2606. 13436v1 Announce Type: new Abstract: Evaluation in machine learning is typically treated as a neutral measurement process.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2606. 09809v1 Announce Type: new Abstract: AI evaluation results are produced at scale but reported inconsistently across leaderboards, model cards, benchmark papers, and company blogs.
The study investigates how prior scores influence large language model (LLM) judgments in the LLM-as-a-Judge paradigm. By testing three prompt conditions—no metadata, revision framing, and anchored metadata containing prior scores—the authors find that prior scores systematically bias evaluations, shifting ratings toward those scores across 192,000 attempts. The bias also affects categorical decisions, blocking 48% of error corrections and flipping 10.18% of correct judgments, and is not mitigated by Chain-of-Thought or a warning, underscoring the need for careful context engineering.
arXiv:2610.33262v1 Announce Type: cross Abstract: We study efficient, adaptive auditing of categorical labels in a fixed dataset, motivated by biodiversity-credit programs in which expert verificatio...
arXiv:2610.07132v1 Announce Type: cross Abstract: Croissant has emerged as a standard for machine-readable dataset metadata, yet populating its fields remains labor-intensive and requires careful rea...
arXiv:2605. 26068v3 Announce Type: replace-cross Abstract: Weakly supervised anomaly detection (WSAD) has developed in three primary directions: incomplete, inexact, and inaccurate supervision.
arXiv:2607. 25891v1 Announce Type: new Abstract: Evaluating AI agents in interactive environments is hindered by fragmented tasks, scaffolds, verifiers, and scoring rules.