# Scoring the Wrong Question: Readout Failures in Constrained-Option Evaluation

arXiv: https://arxiv.org/abs/2609.33179 · HTML: https://mlsanity.com/paper/2609.33179/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 28 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Builds on (most cited first, 25 of 25)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [Large Language Models Are Not Robust Multiple Choice Selectors](https://mlsanity.com/paper/2309.03882/) (2023)
- [Surface Form Competition: Why the Highest Probability Answer Isn't Always Right](https://mlsanity.com/paper/2104.08315/) (2021)
- [Leveraging Large Language Models for Multiple Choice Question Answering](https://mlsanity.com/paper/2210.12353/) (2022)
- [Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences](https://mlsanity.com/paper/2404.12272/) (2024)
- [LM-Polygraph: Uncertainty Estimation for Language Models](https://mlsanity.com/paper/2311.07383/) (2023)
- [Beyond Yes and No: Improving Zero-Shot LLM Rankers via Scoring Fine-Grained Relevance Labels](https://mlsanity.com/paper/2310.14122/) (2023)
- [Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?](https://mlsanity.com/paper/2403.06833/) (2024)
- ["My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models](https://mlsanity.com/paper/2402.14499/) (2024)
- [Perturbation CheckLists for Evaluating NLG Evaluation Metrics](https://mlsanity.com/paper/2109.05771/) (2021)
- [Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think](https://mlsanity.com/paper/2404.08382/) (2024)
- [LLMs can be easily Confused by Instructional Distractions](https://mlsanity.com/paper/2502.04362/) (2025)
- [Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling](https://mlsanity.com/paper/2505.15323/) (2025)
- [PerspectiveGap: A Benchmark for Multi-Agent Orchestration Prompting](https://mlsanity.com/paper/2606.08878/) (2026)
- [Attention Deficits in Language Models: Causal Explanations for Procedural Hallucinations](https://mlsanity.com/paper/2602.19239/) (2026)

## Abstract (arXiv)

Constrained-option scoring reads a model's probabilities for a fixed set of permitted answers, so it returns a score even when the model is about to write something else. We study a prompt that quotes a multiple-choice item, ending in the item's own answer instruction, and asks for a forecast of whether a reader model given only a short note will answer it correctly. The model can begin answering the quoted item: on three Qwen3 checkpoints an answer letter is the most probable token on nearly every passage, and the forecast ranks the reader's correctness indistinguishably from chance. Beyond prior work's argmax check and prefill repair, we contribute a label-free diagnostic of the declared options' support, their first-token mass in context; a deletion test tracing the Qwen3 answer-letter start to the quoted instruction; and rendering and tokenisation checks for dropped separators and coinciding first tokens. Prefilling an answer stem lifts the median option mass from below to above one half on all nine checkpoints scored with this prompt and, with options and renormalisation unchanged, raises the Qwen3-averaged AUC from 0.4929 to 0.6152. lm-polygraph's default P(True) estimator shows a related failure: it reads True where Qwen3 without thinking favours an answer letter (MMLU) or the prompt's (A)/(B) label (TriviaQA), and its Qwen3-averaged AUROC is indistinguishable from chance on MMLU and below chance on TriviaQA. Scoring and renormalising the (A)/(B) labels after an answer stem raises it to 0.632 and 0.868, renormalising True against False in place reaches 0.660 and 0.860, and on TriviaQA both exceed all fourteen default single-answer library estimators. The original forecast is renormalised too, yet stays indistinguishable from chance: option mass flags low support in both settings without labels, and only checking the intended target shows which score still ranks.