Scored vs. Generated Readouts in Behavioral Language Models: An Empirical Study of Elicitation Format

• URL: http://arxiv.org/abs/2609.09882v1
• Date: Wed, 09 Sep 2026 08:37:46 GMT
• Title: Scored vs. Generated Readouts in Behavioral Language Models: An Empirical Study of Elicitation Format
• Abstract summary: We compare probabilities obtained by scoring answer tokens with predictions generated after a written rationale.<n>Across 13 model-domain cells covering four retail tasks, the scored readout ranks outcomes more accurately in 12 of 13 cells.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Language models fine-tuned on customer behavior can predict outcomes and generate explanations, but these readouts are often treated as interchangeable. Holding model checkpoint and prompt content fixed, we compare probabilities obtained by scoring answer tokens with predictions generated after a written rationale. Across 13 model-domain cells covering four retail tasks in three markets, including two using fully public data and checkpoints, the scored readout ranks outcomes more accurately in 12 of 13 cells (two-sided sign test, p approximately 0.003), by 1.5 to 14.5 points in area under the receiver operating characteristic curve (AUC). Paired bootstrap confidence intervals exclude zero in every newly measured cell. The gap varies with task-specific supervision and mismatch between training and serving formats, ranging from -2.2 points for an untuned base model to +13.7 for rationale-format supervision. Analysis of approximately 9,000 rationales identifies two correlates: reduced reliance on the dominant predictive feature and convergence on stock formulations. Probability saturation does not track the gap. A third readout, eliciting a probability before any verdict, improves calibration (Brier score from 0.47 to 0.15) while ranking within noise of scoring, but only for outcome rates represented in training; it is worse than scoring when the scored head is already calibrated. We interpret these differences through the objectives matched by each readout, identify training choices that narrow the gap, and propose retaining generated rationales while sourcing ranking from the scored head.

Related papers

• Target-Checked Reliability Score Refinement for Video Question Answering [3.8271803328378677]
  We study whether answer-level reliability scores can be improved under target shift without retraining the models or changing their answers.<n>We collect option-probability lists from three fixed video-language models under four deterministic video samplings.<n>We compare the original score, defined as the probability assigned to the chosen answer, with a histogram-based gradient-boosting (HGB) score trained on the development datasets.<n>A candidate replaces the original score only when repeated video-level checks indicate a positive, stable improvement.
  arXiv  Detail & Related papers  (2026-09-09T08:29:00Z)
• Anchoring Bias in LLM-as-a-Judge Systems: Prior Scores Compromise Evaluation Independence [0.7340017786387767]
  We show that prior scores, even when included only as context metadata, anchor judgments and systematically shift ratings toward their values.<n>On categorical industry data with human-labeled ground truth, anchored metadata blocks 48% of error corrections and flips 10.18% of correct judgments toward an assigned wrong label.
  arXiv  Detail & Related papers  (2026-08-26T14:41:24Z)
• Recursive Agentic Reasoning [4.7490116928645065]
  Test-time reasoning methods such as iterative refinement, decomposition, and repeated sampling are often evaluated in isolation.<n>We introduce a unified view of these methods as recursion operators over an agent's reasoning trace.<n>We evaluate all three operators against a single-pass chain-of-thought baseline under a shared harness with identical prompts, token budgets, and grading code.
  arXiv  Detail & Related papers  (2026-08-25T01:34:08Z)
• PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception [75.70273182182397]
  PerceptionRubrics is a rubric-based evaluation framework.<n>It addresses the gap between saturated benchmark scores and real-world brittleness.<n>It pairs 1,038 information-dense images with over 10,000 instance-specific rubrics.
  arXiv  Detail & Related papers  (2026-06-26T17:59:15Z)
• Reliable to Expressive: A Curriculum for Rubric-Following Safety Judges [2.8523456804049885]
  Safety judges are increasingly deployed to evaluate model outputs against evolving criteria.<n>Recent meta-evaluation work shows they remain brittle under prompt and rubric variation.<n>We propose a training strategy that combines instance-conditioned dynamic rubrics and a reliable-to-expressive curriculum.
  arXiv  Detail & Related papers  (2026-06-08T08:02:57Z)
• Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning [55.264863369127774]
  Current methods reduce each correct rollout to a single reward bit, ignoring the geometric structure shared among their hidden states.<n>We propose Hidden-Align, an auxiliary loss function that aligns the last-layer hidden states of correct rollouts at the anchor token during RL training, with zero overhead in both training and inference.<n>On eight mathematical reasoning benchmarks, Hidden-Align improves average pass@1 over the DAPO baseline by 3.8, 6.2, and 5.4 percentage points on Qwen3-1.7B, 4B, and 14B respectively, with consistent pass@k gains across all three scales.
  arXiv  Detail & Related papers  (2026-06-02T06:51:15Z)
• What Single-Prompt Accuracy Misses: A Multi-Variant Reliability Audit of Language Models [0.0]
  Single-prompt accuracy is the dominant way to benchmark language models, but it can miss reliability failures that matter.<n>We evaluate a 15-model open-weight corpus, with the main reliability analyses focused on 10 instruct models across five classification and reasoning benchmarks.<n>We find three broad results. First, evaluation design can materially change the conclusion.<n>Second, confidence signals are fragile. On MMLU-Pro, every primary model verbally reports confidence substantially above both its accuracy and its token-probability confidence on the same rows, and verbal parse rate can collapse for a single model on a single prompt variant.
  arXiv  Detail & Related papers  (2026-05-03T20:05:08Z)
• Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents [66.97968363332465]
  We introduce Claw-Eval, an end-to-end evaluation suite addressing all three gaps in agent benchmarks.<n>Claw-Eval comprises 300 human-verified tasks spanning 9 categories across three groups.<n>Every agent action is recorded through three independent evidence channels.
  arXiv  Detail & Related papers  (2026-04-07T17:43:18Z)
• SpatialBench-UC: Uncertainty-Aware Evaluation of Spatial Prompt Following in Text-to-Image Generation [0.0]
  SpatialBench-UC is a small, reproducible benchmark for pairwise spatial relations.<n>We release a benchmark package, versioned prompts, pinned configs, per-sample checker outputs, and report tables.<n>We evaluate three baselines, Stable Diffusion 1.5, SD 1.5 BoxDiff, and SD 1.4 GLIGEN.
  arXiv  Detail & Related papers  (2026-01-19T23:37:10Z)
• Reference-Free Rating of LLM Responses via Latent Information [53.463883683503106]
  We study the common practice of asking a judge model to assign Likert-scale scores to free-text responses.<n>We then propose and evaluate Latent Judges, which derive scalar ratings from internal model signals.<n>Across a broad suite of pairwise and single-rating benchmarks, latent methods match or surpass standard prompting.
  arXiv  Detail & Related papers  (2025-09-29T12:15:52Z)
• Selective Classification Can Magnify Disparities Across Groups [89.14499988774985]
  We find that while selective classification can improve average accuracies, it can simultaneously magnify existing accuracy disparities. Increasing abstentions can even decrease accuracies on some groups. We train distributionally-robust models that achieve similar full-coverage accuracies across groups and show that selective classification uniformly improves each group.
  arXiv  Detail & Related papers  (2020-10-27T08:51:30Z)
• Distribution-free binary classification: prediction sets, confidence intervals and calibration [106.50279469344937]
  We study three notions of uncertainty quantification -- calibration, confidence intervals and prediction sets -- for binary classification in the distribution-free setting. We derive confidence intervals for binned probabilities for both fixed-width and uniform-mass binning. As a consequence of our 'tripod' theorems, these confidence intervals for binned probabilities lead to distribution-free calibration.
  arXiv  Detail & Related papers  (2020-06-18T14:17:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.