arXiv Machine Learning
Beyond Aggregate Accuracy: Item-Level Transitions in Prompt Optimization
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Aug 12
RLMOpt: Adaptive Prompt Optimization via Recursive Language Models
arXiv:2608. 10471v1 Announce Type: new Abstract: Prompt optimizers automate the search for prompts that improve language-model performance, but existing methods rely on a predefined optimization procedure: the algorithm determines which candidates to explore and how the search progresses, while the language model generates or refines prompt proposals.
arXiv AI
Sep 11
Scored vs. Generated Readouts in Behavioral Language Models: An Empirical Study of Elicitation Format
The study compares two ways of obtaining predictions from language models fine‑tuned on customer behavior: scoring answer tokens directly versus generating a written rationale and then scoring the resulting answer. Across 13 model‑domain cells covering four retail tasks, scored readouts consistently rank outcomes more accurately than generated readouts, with an AUC improvement ranging from 1.5 to 14.5 points. The authors also find that a third readout—eliciting a probability before any verdict—improves calibration but only when outcome rates are represented in training, and they recommend using generated rationales for interpretability while relying on scored heads for ranking.
arXiv Computation and Language
Sep 11
Rethinking Verbalized Confidence for LLM-as-a-Judge: A Compatibility Shift on Post-2025 Proprietary Models
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.
arXiv AI
Aug 25
GIM: Evaluating models via tasks that integrate multiple cognitive domains
The paper introduces the Grounded Integration Measure (GIM), a benchmark of 820 expert‑authored problems designed to test models on tasks that integrate multiple cognitive operations such as constraint satisfaction, state tracking, epistemic vigilance, and audience calibration. GIM emphasizes realistic, broadly accessible knowledge rather than specialized expertise, and uses a judge‑aware 2‑parameter logistic IRT model to produce robust ability estimates across 53 model‑thinking‑level configurations. The authors provide a comprehensive leaderboard of 22 models and 47 test configurations, and conduct an extensive study on how test‑time compute affects model capability, finding that configuration choices like thinking budget and quantization can be as influential as model selection itself. whyItMatters":"By focusing on integration of multiple cognitive domains, GIM offers a more realistic assessment of model reasoning capabilities than benchmarks that either overemphasize memorization or abstract reasoning alone."
arXiv Computation and Language
Oct 23
Behind Aggregate Scores: What Systematically Varying Arena-Hard's LLM Judge Reveals
The paper investigates the reliability of LLM judges in the Arena-Hard benchmark, showing that aggregate scores can mask significant variability in individual verdicts. By running GPT‑4.1 across 500 prompts under eight different judge configurations and repeating each setup, the authors find that small changes—whether in temperature, criteria, or instruction framing—can shift win/tie/loss outcomes on up to 28% of prompts and alter aggregate scores by several points. The study concludes that stable aggregate scores do not guarantee repeatable individual judgments, and recommends that evaluations report both aggregate results and prompt‑level agreement.
arXiv AI
Jul 1
Contrastive Reflection for Iterative Prompt Optimization
arXiv:2606. 30840v1 Announce Type: new Abstract: LLM agents are becoming central to information retrieval: they issue retrieval queries, synthesize answers, and increasingly serve as judges for IR evaluation.