# Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large Language Models

arXiv: https://arxiv.org/abs/2606.03165 · HTML: https://mlsanity.com/paper/2606.03165/

## 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 38 of its 83 references that are in the map.
- First posted on arXiv 2 Jun 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, 30 of 38)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [The Falcon Series of Open Language Models](https://mlsanity.com/paper/2311.16867/) (2023)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [The Curse of Recursion: Training on Generated Data Makes Models Forget](https://mlsanity.com/paper/2305.17493/) (2023)
- [Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection](https://mlsanity.com/paper/2004.10643/) (2020)
- [Self-Consuming Generative Models Go MAD](https://mlsanity.com/paper/2307.01850/) (2023)
- [Does Writing with Language Models Reduce Content Diversity?](https://mlsanity.com/paper/2309.05196/) (2023)
- [Mapping the Increasing Use of LLMs in Scientific Papers](https://mlsanity.com/paper/2404.01268/) (2024)
- [Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity](https://mlsanity.com/paper/2510.01171/) (2025)
- [Testing of Detection Tools for AI-Generated Text](https://mlsanity.com/paper/2306.15666/) (2023)
- [Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loop](https://mlsanity.com/paper/2311.16822/) (2023)
- [Research Priorities for Robust and Beneficial Artificial Intelligence](https://mlsanity.com/paper/1602.03506/) (2016)
- [On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization](https://mlsanity.com/paper/2405.16455/) (2024)
- [One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity](https://mlsanity.com/paper/2411.04427/) (2024)
- [What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability](https://mlsanity.com/paper/2305.11707/) (2023)
- [From Lists to Emojis: How Format Bias Affects Model Alignment](https://mlsanity.com/paper/2409.11704/) (2024)

## Abstract (arXiv)

The language used by digital chat assistants such as ChatGPT can diverge from human expectations (misalignment). Research, mostly on Scientific English, has described both what divergences occur and, to some extent, why, linking them to the training stage of human preference learning. Yet, existing approaches rely on manual curation. This paper introduces two curation-free, assumption-light evaluation metrics: the Lexical Alignment Score, which identifies lexical overuse, and the Triangulated Preference Shift, which quantifies how much of such shifts can be attributed to human preference learning. Using PubMed abstracts, continuations were generated and measured using windowed document prevalence across six model families (Falcon, Gemma, Llama, Mistral, OLMo, Yi). The procedure identifies, without manual intervention, overused items such as 'suggest', 'additionally', and 'strategy', and estimates their link to preference learning. Our findings replicate prior work and remain stable across parameter settings, random seeds, and evaluation on further data. The approach scales readily and enables systematic study of lexical (mis)alignment beyond Scientific English and across languages, and as such, the metrics have the potential to contribute to improved alignment for future models and understanding of its origins.