Jev has the lowest cost and median response time among the evaluated configurations, while hosted language models achieve higher baseline accuracy and Rankings by baseline accuracy differ from rankings by correctness across every condition and repeat, although small differences in the latter do not establish a general stability advantage.
Abstract
Aggregate accuracy summarizes how often a model is correct, but not which judgments remain correct when requests change. We evaluate Jev and nine language models on ContractNLI, with repeated requests that preserve the contract and target while varying visible hypotheses, requested answers, and output order. A four-model follow-up adds an equal-call repetition control and coverage of the remaining test contracts. Corrections and regressions can cancel, leaving unchanged accuracy despite changed decisions; consistent answers can also preserve errors. Majority voting over recorded responses yields small, uncertain gains, with repeated wrong answers accounting for much of the observed error. Gold-class diagnostics further reveal different error profiles behind aggregate model rankings. Resource comparisons add distinct trade-offs: Jev is cheapest and fastest for the joint baseline, while hosted language models achieve higher accuracy. Together, these findings connect decision-level evaluation to whether additional calls improve correctness and what the resulting decisions cost.
The paper argues for evaluation procedures that disclose the tested configuration, validate questions and successful task completion, report performance alongside cost and execution time, and make the scope of generalization explicit, and discusses Isotanta, a crowdsourced benchmarking platform, as a practical example...
Language models tend to agree with whatever a user asserts, and post-training increasingly targets this sycophancy so that models evaluate claims on their merits rather than deferring to the user. Yet the same models are far more compliant when a wrong answer is attributed to a verified source, which is how retrieval r...
Abhinav Kumar, Paras Chopra· arXiv.org· 4 citations· ⚡1
Large language models (LLMs) are increasingly used to draft contractual language, yet conventional accuracy or preference-based evaluations are poorly matched to legal drafting. A clause may be fluent and stylistically polished while still omitting an essential carve-out, allocating risk in an unenforceable way, assumi...
It is found that answers with smaller cross-contextual shifts are more likely to be correct or factual, and C3 provides a complementary axis of evaluation and can serve as a benchmark usefulness diagnostic, identifying which portions of a benchmark remain informative even when aggregated scores are widely considered"sa...
Probity, a benchmark of 60 tasks and 470 items from real venture-financing filings, is built and a defect any excerpt-built benchmark can carry is found: items whose evidence is missing from the window of text the model is shown.
Legal work, with its heavy reliance on processing large amounts of text, is often considered one of the domains most exposed to the use of LLMs. Contract ``scrubbing,''the final review of transactional agreements for errors and inconsistencies, is a particularly suitable task for automation, because it is routine, pain...
Yejin Bang, Kirsty Fielding, Brandan Oliver et al.· 0 citations