ICLR Poster Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models
ICLR 2026
CSP Test<br>-->
Poster
Fri, Apr 24, 2026 • 11:15 AM – 1:45 PM PDT
Pavilion 3 P3-#419
Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models
Sam Paech ⋅ Allen Roush ⋅ Judah Goldfeder ⋅ Ravid Shwartz-Ziv
Project Page
Abstract
Repetitive lexical patterns in LLM output, termed "slop," degrade writing quality through over-use and make 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. and, (3) Final Token Preference Optimization (FTPO), a novel fine-tuning method that operates in logit-space on individual tokens, surgically adjusting logits wherever a banned pattern has appeared in an inference trace. We demonstrate that some slop patterns appear over 1,000 times 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 datasets under MIT license.
Show more
Log in and register to view live content
Successful Page Load
ICLR uses cookies for essential functions only. We do not sell your personal<br>information.<br>Our Privacy Policy "
Accept