# Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models

arXiv: https://arxiv.org/abs/2510.15061 · HTML: https://mlsanity.com/paper/2510.15061/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Builds on (most cited first, 22 of 22)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [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)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [Understanding the Effects of RLHF on LLM Generalisation and Diversity](https://mlsanity.com/paper/2310.06452/) (2023)
- [Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs](https://mlsanity.com/paper/2407.01082/) (2024)
- [Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training](https://mlsanity.com/paper/1911.03860/) (2019)
- [A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions](https://mlsanity.com/paper/2310.14724/) (2023)
- [β-DPO: Direct Preference Optimization with Dynamic β](https://mlsanity.com/paper/2407.08639/) (2024)
- [EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models](https://mlsanity.com/paper/2312.06281/) (2023)
- [One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity](https://mlsanity.com/paper/2411.04427/) (2024)
- [Diverse Preference Optimization](https://mlsanity.com/paper/2501.18101/) (2025)
- [The Price of Format: Diversity Collapse in LLMs](https://mlsanity.com/paper/2505.18949/) (2025)
- [Backtracking Improves Generation Safety](https://mlsanity.com/paper/2409.14586/) (2024)
- [Suppressing Pink Elephants with Direct Principle Feedback](https://mlsanity.com/paper/2402.07896/) (2024)
- [Most Language Models can be Poets too: An AI Writing Assistant and Constrained Text Generation Studio](https://mlsanity.com/paper/2306.15926/) (2023)
- [Negative Lexical Constraints in Neural Machine Translation](https://mlsanity.com/paper/2308.03601/) (2023)

## Built on by (most cited first, 1 of 1)

- [Don't Repeat Yourself: Stopping Verbatim Loops at Sampling Time](https://mlsanity.com/paper/2608.22761/) (2026)

## Abstract (arXiv)

Widespread LLM adoption has introduced characteristic repetitive phraseology, termed "slop," which degrades output quality and makes AI-generated text immediately recognizable. We present Antislop, a comprehensive framework providing tools to both detect and eliminate these overused patterns. Our approach combines three innovations: (1) The Antislop Sampler, which uses backtracking to suppress unwanted strings at inference time without destroying vocabulary; (2) An automated pipeline that profiles model-specific slop against human baselines and generates training data; (3) Final Token Preference Optimization (FTPO), a novel fine-tuning method that operates on individual tokens, surgically adjusting logits wherever a banned pattern has appeared in an inference trace. We demonstrate that some slop patterns appear over 1,000x more frequently in LLM output than human text. The Antislop Sampler successfully suppresses 8,000+ patterns while maintaining quality, whereas token banning becomes unusable at just 2,000. Most importantly, FTPO achieves 90% slop reduction while maintaining or improving performance in cross-domain evals including GSM8K, MMLU, and creative writing tasks. In contrast, DPO suffers significant degradation in writing quality and lexical diversity despite achieving weaker suppression. We release all code and results under MIT license: https://github.com/sam-paech/auto-antislop.