Flip-Flop Consistency: Unsupervised Training for Robustness to Prompt Perturbations in LLMs

• URL: http://arxiv.org/abs/2510.14242v1
• Date: Thu, 16 Oct 2025 02:54:01 GMT
• Title: Flip-Flop Consistency: Unsupervised Training for Robustness to Prompt Perturbations in LLMs
• Abstract summary: Large Language Models (LLMs) often produce inconsistent answers when faced with different phrasings of the same prompt.<n>We propose Flip-Flop Consistency ($F2C$), an unsupervised training method that improves robustness to such perturbations.<n>We evaluate our method on 11 datasets spanning four NLP tasks, with 4-15 prompt variations per dataset.
• Score: 2.125148574616104
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Scaling Laws for Agent Harnesses via Effective Feedback Compute [53.68149869349268]
  emphEffective Feedback Compute (EFC) is a trace-level scaling coordinate that credits feedback only when it is informative, valid, non-redundant, and retained for subsequent decisions.<n>EFC-based coordinates consistently predict failure rates better than raw-compute baselines.
  arXiv  Detail & Related papers  (2026-05-28T09:45:47Z)
• High-Probability Convergence in Decentralized Stochastic Optimization with Gradient Tracking [69.90407799170687]
  We study high-probability (HP) convergence guarantees in decentralized optimization.<n>Our results establish the same conditions on the horizon as in achieving comparable times.
  arXiv  Detail & Related papers  (2026-04-30T22:45:21Z)
• $V_1$: Unifying Generation and Self-Verification for Parallel Reasoners [69.66089681814013]
  $V_$ is a framework that unifies generation and verification through efficient pairwise ranking.<n>$V_$-Infer improves Pass@1 by up to $10%$ over pointwise verification.<n>$V_$-PairRL achieves $7$--$9%$ test-time scaling gains over standard RL and pointwise joint training.
  arXiv  Detail & Related papers  (2026-03-04T17:22:16Z)
• When Does Margin Clamping Affect Training Variance? Dataset-Dependent Effects in Contrastive Forward-Forward Learning [0.0]
  Contrastive Forward-Forward (CFF) learning trains Vision Transformers layer by layer against supervised contrastive objectives.<n>We focus on one implementation detail: the positive-pair margin in the contrastive loss is applied through saturating similarity clamping.<n>We prove that an alternative formulation, subtracting the margin after the log-probability, is gradient-neutral under the mean-over-positives reduction.
  arXiv  Detail & Related papers  (2026-03-01T07:00:38Z)
• High-Dimensional Robust Mean Estimation with Untrusted Batches [38.14592862692954]
  We study high-dimensional mean estimation in a collaborative setting where data is contributed by $N$ users in batches of size $n$.<n>We formalize this challenge through a double corruption landscape: an $varepsilon$-fraction of users are entirely adversarial, while the remaining good'' users provide data from distributions that are related to $P$, but deviate by a proximity parameter $$.<n>Our algorithms achieve the minimax-optimal error rate $O(sqrtvarepsilon/n + sqrtd/nN + s
  arXiv  Detail & Related papers  (2026-02-24T08:59:37Z)
• Fast-Decoding Diffusion Language Models via Progress-Aware Confidence Schedules [25.251683954675958]
  We present SchED, a training-free, model-agnostic early-exit algorithm.<n>SchED aggregates full-span logit margins and halts decoding once a smooth, progress-dependent confidence threshold is met.<n>We show that SchED is robust and clearly outperforms prior confidence-based early-exit methods.
  arXiv  Detail & Related papers  (2025-12-02T16:01:08Z)
• Closing the Approximation Gap of Partial AUC Optimization: A Tale of Two Formulations [121.39938773554523]
  The Area Under the ROC Curve (AUC) is a pivotal evaluation metric in real-world scenarios with both class imbalance and decision constraints.<n>We present two simple instance-wise minimax reformulations to close the approximation gap of PAUC optimization.<n>The resulting algorithms enjoy a linear per-iteration computational complexity w.r.t. the sample size and a convergence rate of $O(-2/3)$ for typical one-way and two-way PAUCs.
  arXiv  Detail & Related papers  (2025-12-01T02:52:33Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)
• Do Repetitions Matter? Strengthening Reliability in LLM Evaluations [0.374750127323442]
  LLM leaderboards often rely on single runs, but how many repetitions are required for reliable conclusions remains unclear.<n>We re-evaluated eight state-of-the-art models on the AI4Math Benchmark with three independent runs per setting.
  arXiv  Detail & Related papers  (2025-09-28T21:45:20Z)
• DRO-REBEL: Distributionally Robust Relative-Reward Regression for Fast and Efficient LLM Alignment [0.0]
  Reinforcement learning with human feedback (RLHF) has become crucial for aligning Large Language Models (LLMs) with human intent.<n>We introduce DRO-REBEL, a unified family of robust REBEL updates with type-$p$ Wasserstein, KL, and $chi2$ ambiguity sets.<n>Using Fenchel duality, each update reduces to a simple relative-reward regression, preserving scalability and avoiding PPO-style clipping or auxiliary value networks.
  arXiv  Detail & Related papers  (2025-09-23T14:49:48Z)
• FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA [68.44043212834204]
  Low-Rank Adaptation (LoRA) is widely used for efficient fine-tuning of language models in learning (FL)<n>Low-Rank Adaptation (LoRA) is widely used for efficient fine-tuning of language models in learning (FL)
  arXiv  Detail & Related papers  (2025-05-19T07:32:56Z)
• Towards a Sharp Analysis of Offline Policy Learning for $f$-Divergence-Regularized Contextual Bandits [49.96531901205305]
  We analyze $f$-divergence-regularized offline policy learning.<n>For reverse Kullback-Leibler (KL) divergence, we give the first $tildeO(epsilon-1)$ sample complexity under single-policy concentrability.<n>We extend our analysis to dueling bandits, and we believe these results take a significant step toward a comprehensive understanding of $f$-divergence-regularized policy learning.
  arXiv  Detail & Related papers  (2025-02-09T22:14:45Z)
• The Differences Between Direct Alignment Algorithms are a Blur [3.0059120458540383]
  We show that one-stage methods (e.g. ORPO, ASFT) underperform compared to two-stage approaches.<n>We demonstrate that adapting them to a two-stage setup with an explicit SFT phase can improve their performance.<n>Our comprehensive analysis reveals that the choice between pairwise and pointwise objectives is the primary determinant of alignment success.
  arXiv  Detail & Related papers  (2025-02-03T10:54:14Z)
• FABind: Fast and Accurate Protein-Ligand Binding [127.7790493202716]
  $mathbfFABind$ is an end-to-end model that combines pocket prediction and docking to achieve accurate and fast protein-ligand binding. Our proposed model demonstrates strong advantages in terms of effectiveness and efficiency compared to existing methods.
  arXiv  Detail & Related papers  (2023-10-10T16:39:47Z)
• Noise Stability Optimization for Finding Flat Minima: A Hessian-based Regularization Approach [18.009376840944284]
  We present an algorithm that can effectively regularize the Hessian loss matrices leading to regions with bound loss surfaces. Our approach is effective for improving generalization in pretraining CLIP and chain-of-thought fine-tuning datasets.
  arXiv  Detail & Related papers  (2023-06-14T14:58:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.