The study investigates whether Jev, a typed classifier that outputs probabilities over allowed answers without generating text, can replace large language model (LLM) rubric judges. Across nine panels from seven benchmarks, Jev’s accuracy differed significantly from LLM judges in only 8 of 27 paired comparisons, performing best on binary criteria and worse only on graded ones, while most other comparisons were inconclusive. In terms of cost and speed, Jev was 29 to 325 times cheaper and 30 to 220 times faster than the flash‑tier LLM judges, and a cascade approach that defers uncertain Jev verdicts to an LLM yielded only modest gains.
whyItMatters":"The findings suggest that a lightweight classifier like Jev can serve as an efficient first‑stage evaluator, potentially reducing the reliance on expensive and slow LLM judges in automated grading pipelines."
By Delip Rao, Chris Callison-Burch
The study compares Jev, a typed classifier that outputs probabilities over allowed answers, with three flash-tier LLM rubric judges across nine panels from seven benchmarks. Jev’s accuracy differs significantly from an LLM judge in only 8 of 27 paired comparisons, performing best on binary criteria and worse only on graded ones, while most other comparisons are inconclusive. In terms of cost and speed, Jev is 29 to 325 times cheaper and 30 to 220 times faster than the LLM judges, and a cascade that defers uncertain Jev verdicts to an LLM yields only modest gains of up to 2.0 points over the best single judge.
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.
By Ante Kapetanovic, Kemal Altwlkany, Andro Mercep, Tomislav Duricic, Emanuel Lacic
The paper evaluates whether zero‑shot large language models (LLMs) can replace fine‑tuned natural language understanding (NLU) classifiers for intent detection in conversational systems. Experiments on ATIS and CLINC150 show that fine‑tuned RoBERTa outperforms Claude Haiku zero‑shot when ample in‑domain labels are available, but the LLM matches the supervised model on the broader 150‑intent CLINC150 schema. The authors identify three production‑relevant scenarios where LLMs excel—out‑of‑scope detection, robustness to ASR noise, and dynamic per‑deployment schemas—and present a decision framework to guide practitioners.
whyItMatters:"The study provides concrete evidence and a practical framework for deciding when to deploy LLMs versus fine‑tuned models in real‑world conversational applications."
By Carson Rodrigues, Oysturn Vas
arXiv:2610.20417v1 Announce Type: new
Abstract: Audits of large language model (LLM) extraction from full-length documents report severe unreliability, leaving two questions open: what the failures a...
By Jiahong Qian
arXiv:2606. 00467v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for zero-shot annotation and LLM-as-a-judge tasks, yet their reliability hinges on how model-internalized priors interact with user-provided instructions.
By Etienne Casanova, Rafal Kocielnik, R. Michael Alvarez
arXiv:2610.18415v1 Announce Type: cross
Abstract: Large Language Models (LLMs) are aligned to human preferences, after pre-training and supervised fine-tuning steps. However, standard RL alignment st...
By Pratuat Amatya, Vinay Setty, V Venktesh, Avishek Anand
The study investigates whether large language models (LLMs) can identify code they have generated, potentially leading to self‑favoring or collusive behavior. Experiments across 15 model‑benchmark pairs show that models can attribute authorship with balanced accuracy between 49% and 58%, but this ability largely stems from superficial cues such as solution length. Removing surface features like docstrings, comments, and type hints reduces attribution accuracy to chance, indicating that surface cues drive the effect.
By Ehsan Barkhordar, Surendrabikram Thapa
arXiv:2610.05094v1 Announce Type: cross
Abstract: Researchers increasingly use Large Language Models as judges (LLM-as-a-judge) to evaluate model outputs. Yet there are no standards for how to design...
By Laur\`ene Vaugrante, Thilo Hagendorff
The paper evaluates nine on‑device named‑entity recognition models ranging from classical taggers to large language models, measuring not only accuracy but also latency and output validity. Using a silver‑gold benchmark derived from an LLM judge panel and a human‑validated corpus, the study shows that encoder‑based models achieve comparable accuracy to a 4 B instruct LLM while being much smaller, faster, and producing no malformed output. Confidence calibration of GLiNER is analyzed, revealing over‑confidence but improved reliability after temperature scaling and thresholding.
By Vinay Kumar Chaganti
The study audits large language model (LLM) outputs by measuring how well repeated queries recover a collected set of responses versus the full set of possible outputs. Using sample-based rarefaction on 4,500 responses from 50 buying questions across six configurations, the authors find historical-dictionary median recovery rates between 92.6% and 95.2%, which drop to 89.5%–94.7% after re‑adjudicating all candidate strings. Additional analyses with Gemini 3.1 Pro annotations and matched roster data confirm that recovery percentages vary with extraction methods, question selection, and the finite reference collection, underscoring the need for explicit measurement definitions and sensitivity analyses in LLM audits.
By Dmitrij \.Zatuchin
The paper argues that verbalized confidence—once viewed as overconfident and coarse—has become the preferred soft‑scoring method for LLM‑as‑a‑Judge on top‑tier proprietary models released after 2025. Experiments on SummEval, AggreFact, and HelpSteer2 across up to 18 LLMs show that log‑probabilities are no longer the best signal, and that adding an overconfidence advisory and self‑debate further improves calibration and robustness. The authors note that these enhancements incur little accuracy loss on post‑2025 models but do affect pre‑2025 ones, highlighting a compatibility shift in how confidence should be measured.
By Yu-Chung Hsiao