- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper investigates whether model-generated rubrics reward responses that violate the available evidence. ImpossibleRubrics contains 169 impossible tasks and 48 answerable controls. An attack succeeds when it violates the task certificate while scoring at least as highly as an honest reference answer. Under a fixed evaluation chain, eleven generators achieve exploitation rates of 8–26% on Full-150 and 36–98% on the selected Hard-45 set. Additional experiments examine resampling, model substitutions, and prompting interventions, and reveal substantial dependence on the verifier configuration.
Critical strengths
-
The research question has practical relevance. Generated rubrics can guide evaluation, response selection, and training rewards, making erroneous incentives an important concern. Figures 1–2 provide an intuitive example in which the rubric incorrectly interprets missing evidence as zero probability and rewards an unsupported response more highly than an honest one.
-
The benchmark design is reusable. Retaining tasks, evidence packets, and certificates rather than fixing the evaluated rubrics allows the framework to assess new generators and generation strategies. The closed-evidence setting also facilitates inspection of whether individual scoring criteria require unsupported conclusions.
-
Some controlled analyses provide useful diagnostic information. In particular, freezing responses and scores while changing only the verifier directly demonstrates sensitivity to the verification protocol. This finding can inform the design and interpretation of future rubric-exploitation evaluations.
Critical weaknesses
-
The connection between adversarial exploitability and actual training risk is not established. The main experiments use a targeted attacker that can inspect the rubric and is instructed to disregard honesty, without testing whether a policy discovers and amplifies these exploits during reward optimization. The only benign best-of-N experiment instead reduces violations from 44.4% under random selection to 27.8%. Whether the metric predicts reward exploitation or declining honesty during training therefore remains unvalidated.
-
The reliability of the core labels and reference answers remains insufficiently established. In Appendix M, exploitation on identical responses changes from 33.3% to 75.6% across verifiers, and some honest references contain omitted certificate requirements or source-attribution problems. The existing single-author, 40-item calibration does not adjudicate these new disagreements. Exploitation rates and model comparisons consequently require independent validation.
-
The generation-strategy baselines are insufficient. The main experiments use a common default prompt, and the mitigation experiment tests only one generic safety instruction. The certificate-faithful baseline has privileged task information, while the decisiveness-oriented baseline does not represent a competitive generation procedure. Matched-input evidence-analysis, rubric-checking, or revision baselines are missing, limiting conclusions about whether the failures persist across reasonable generation strategies.
-
Key validation experiments insufficiently cover the models underlying the main comparative claims. Full-Hard-45 resampling primarily covers three earlier Claude generators, while the supplementary GPT-5.6-sol study covers only 20 environments. Answerable controls exclude the leading Opus 5 and GPT-5.6 configurations and the safety-prompted settings. The stability of the leading models’ advantages, and whether lower exploitation comes with increased over-refusal, therefore remain insufficiently tested.
-
The benchmark’s distinctive diagnostic value is unclear. Its main novelty lies in evaluating rubric generators, but the experiments do not adequately distinguish rubric-construction errors from the generator’s underlying evidence-understanding errors. A matched comparison with direct answering or answerability judgments is missing, leaving unclear how much additional information the benchmark provides beyond evidence-understanding and abstention evaluation.
Questions for authors
Questions For Authors
-
As reward optimization becomes stronger, do rubric scores increase while independently assessed evidence faithfulness decreases? Can a controlled optimization experiment test the relationship between adversarial exploitation rates and actual optimization risk?
-
Under the same question-and-evidence input budget, do evidence-analysis-first generation or rubric-checking and revision procedures reduce exploitation? Do the main model differences persist?
-
Can representative leading and comparison models be evaluated across repeated rubric draws on a common task set, reporting both impossible-task exploitation and answerable-task over-refusal?
-
How much do a model’s direct-answering errors overlap with its rubric-generation failures? Are there cases where the model correctly identifies insufficient evidence but nevertheless generates erroneous scoring criteria?
Dear reviewers,
Thank you for your reviews. Please read the authors’ response and follow up in the discussion, briefly indicating whether your main concerns have been addressed and highlighting any remaining questions. Please also update your review and rating where appropriate.
Many thanks for your time and effort.