{"ID":2854379,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.14242","arxiv_id":"2510.14242","title":"Flip-Flop Consistency: Unsupervised Training for Robustness to Prompt Perturbations in LLMs","abstract":"Large Language Models (LLMs) often produce inconsistent answers when faced with different phrasings of the same prompt. In this paper, we propose Flip-Flop Consistency ($F^2C$), an unsupervised training method that improves robustness to such perturbations. $F^2C$ is composed of two key components. The first, Consensus Cross-Entropy (CCE), uses a majority vote across prompt variations to create a hard pseudo-label. The second is a representation alignment loss that pulls lower-confidence and non-majority predictors toward the consensus established by high-confidence, majority-voting variations. We evaluate our method on 11 datasets spanning four NLP tasks, with 4-15 prompt variations per dataset. On average, $F^2C$ raises observed agreement by 11.62%, improves mean $F_1$ by 8.94%, and reduces performance variance across formats by 3.29%. In out-of-domain evaluations, $F^2C$ generalizes effectively, increasing $\\overline{F_1}$ and agreement while decreasing variance across most source-target pairs. Finally, when trained on only a subset of prompt perturbations and evaluated on held-out formats, $F^2C$ consistently improves both performance and agreement while reducing variance. These findings highlight $F^2C$ as an effective unsupervised method for enhancing LLM consistency, performance, and generalization under prompt perturbations. Code is available at https://github.com/ParsaHejabi/Flip-Flop-Consistency-Unsupervised-Training-for-Robustness-to-Prompt-Perturbations-in-LLMs.","short_abstract":"Large Language Models (LLMs) often produce inconsistent answers when faced with different phrasings of the same prompt. In this paper, we propose Flip-Flop Consistency ($F^2C$), an unsupervised training method that improves robustness to such perturbations. $F^2C$ is composed of two key components. The first, Consensus...","url_abs":"https://arxiv.org/abs/2510.14242","url_pdf":"https://arxiv.org/pdf/2510.14242v1","authors":"[\"Parsa Hejabi\",\"Elnaz Rahmati\",\"Alireza S. Ziabari\",\"Morteza Dehghani\"]","published":"2025-10-16T02:54:01Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":608145,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2854379,"paper_url":"https://arxiv.org/abs/2510.14242","paper_title":"Flip-Flop Consistency: Unsupervised Training for Robustness to Prompt Perturbations in LLMs","repo_url":"https://github.com/ParsaHejabi/Flip-Flop-Consistency-Unsupervised-Training-for-Robustness-to-Prompt-Perturbations-in-LLMs","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}