# Do Reviewers Still Reward Lexical Complexity? A Frozen-Rater Study of Preference Drift in 124K ICLR Reviews

arXiv: https://arxiv.org/abs/2609.08475 · HTML: https://mlsanity.com/paper/2609.08475/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 26 of its 54 references that are in the map.
- First posted on arXiv 8 Sep 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 26 of 26)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge](https://mlsanity.com/paper/2410.02736/) (2024)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [Performative Prediction](https://mlsanity.com/paper/2002.06673/) (2020)
- [Strategic Classification](https://mlsanity.com/paper/1506.06980/) (2015)
- [Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews](https://mlsanity.com/paper/2403.07183/) (2024)
- [Benchmarking Cognitive Biases in Large Language Models as Evaluators](https://mlsanity.com/paper/2309.17012/) (2023)
- [Mapping the Increasing Use of LLMs in Scientific Papers](https://mlsanity.com/paper/2404.01268/) (2024)
- [Delving into LLM-assisted writing in biomedical publications through excess vocabulary](https://mlsanity.com/paper/2406.07016/) (2024)
- [The AI Review Lottery: Widespread AI-Assisted Peer Reviews Boost Paper Scores and Acceptance Rates](https://mlsanity.com/paper/2405.02150/) (2024)
- [Inconsistency in Conference Peer Review: Revisiting the 2014 NeurIPS Experiment](https://mlsanity.com/paper/2109.09774/) (2021)
- [Are We There Yet? Revealing the Risks of Utilizing Large Language Models in Scholarly Peer Review](https://mlsanity.com/paper/2412.01708/) (2024)
- [Has the Machine Learning Review Process Become More Arbitrary as the Field Has Grown? The NeurIPS 2021 Consistency Experiment](https://mlsanity.com/paper/2306.03262/) (2023)
- [Peer Reviews of Peer Reviews: A Randomized Controlled Trial and Other Experiments](https://mlsanity.com/paper/2311.09497/) (2023)
- [How LLMs Distort Our Written Language](https://mlsanity.com/paper/2603.18161/) (2026)
- [What's Trending in Difference-in-Differences? A Synthesis of the Recent Econometrics Literature](https://mlsanity.com/paper/2201.01194/) (2022)
- [On Testing for Biases in Peer Review](https://mlsanity.com/paper/1912.13188/) (2019)
- [How much are LLMs changing the language of academic papers after ChatGPT? A multi-database and full text analysis](https://mlsanity.com/paper/2509.09596/) (2025)
- [Who Drifted: the System or the Judge? Anytime-Valid Attribution in LLM Evaluation Pipelines](https://mlsanity.com/paper/2606.15474/) (2026)
- [When the Judge Changes, So Does the Measurement: Auditing LLM-as-Judge Reliability](https://mlsanity.com/paper/2607.08535/) (2026)
- [Analyzing Linguistic Complexity and Scientific Impact](https://mlsanity.com/paper/1907.11843/) (2019)
- [What Drives Paper Acceptance? A Process-Centric Analysis of Modern Peer Review](https://mlsanity.com/paper/2509.25701/) (2025)
- [Examining Scientific Writing Styles from the Perspective of Linguistic Complexity](https://mlsanity.com/paper/1807.08374/) (2018)

## Abstract (arXiv)

Large language models have collapsed the cost of producing lexically elaborate prose, and whether peer reviewers still reward it is a question about the evaluator, not about the text. When the association between a writing cue and review scores moves across years, the reviewers may have changed, the submissions may have changed, or both, and a regression of scores on text cannot say which. We separate the two with a frozen rater: 81,850 machine reviews of ICLR submissions from 2018 to 2025, all generated in one February-April 2025 window with one model family and one prompt, so that its year-to-year coefficients track submission composition alone and the human-minus-frozen trend difference identifies reviewer preference drift. On 32,638 submissions with 124,615 human reviews, the human coefficient on non-domain lexical complexity falls from +0.142 to -0.015 while the frozen rater moves from +0.080 to +0.082; the three-way difference-in-differences is -0.0100 (q=0.013), and forty random-wordlist placebos through the same specification centre on zero. Humans still reward sentence-length variability, which the frozen rater never registers, while the frozen rater still pays for lexical complexity at its earlier rate. Every claim is held to a double gate of false-discovery control and interval exclusion, and the findings that failed adversarial re-testing are reported. Reviewers discounted a cue whose production cost collapsed, as models of manipulable signals prescribe; an LLM judge calibrated to historical human preferences inherits the earlier schedule and drifts out of alignment while its agreement with humans on totals stays ordinary.