A Voter-Based Stochastic Rejection-Method Framework for Asymptotically Safe Language Model Outputs

• URL: http://arxiv.org/abs/2407.16994v3
• Date: Sun, 28 Sep 2025 18:15:48 GMT
• Title: A Voter-Based Stochastic Rejection-Method Framework for Asymptotically Safe Language Model Outputs
• Abstract summary: We propose an approach for preventing unsafe or otherwise low-quality large language model (LLM) outputs by leveraging theity of LLMs.<n>In this system, LLM checkers vote on the acceptability of a generated output, regenerating it if a threshold of disapproval is reached.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose an approach for preventing unsafe or otherwise low-quality large language model (LLM) outputs by leveraging the stochasticity of LLMs, an approach we call Repeated Checking with Regeneration (RCR). In this system, LLM checkers vote on the acceptability of a generated output, regenerating it if a threshold of disapproval is reached, until sufficient checkers approve. Based on our estimators for cost and failure rate and experimental data tailored to the application, our algorithm achieves a desired expected failure rate at Pareto-optimal cost. The failure rate provably decreases exponentially as a function of cost, and the models reasonably estimate the actual performance of such a system in action, even with limited data. This approach does not depend on the language model used, and could allow cheap, small LLMs to control, constrain, or at some tasks even outperform very complex and costly ones.

Related papers

• LLM Readiness Harness: Evaluation, Observability, and CI Gates for LLM/RAG Applications [51.56484100374058]
  We present a readiness harness for LLM and RAG applications that turns evaluation into a deployment decision workflow.<n>The system combines automated benchmarks, OpenTelemetry observability, and CI quality gates under a minimal API contract.<n>We evaluate the harness on ticket-routing and BEIR tasks with full Azure matrix coverage.
  arXiv  Detail & Related papers  (2026-03-28T18:03:32Z)
• ODAR: Principled Adaptive Routing for LLM Reasoning via Active Inference [60.958331943869126]
  ODAR-Expert is an adaptive routing framework that optimize the accuracy-efficiency trade-off via principled resource allocation.<n>We show strong and consistent gains, including 98.2% accuracy on MATH and 54.8% on Humanity's Last Exam.
  arXiv  Detail & Related papers  (2026-02-27T05:22:01Z)
• Conformal Thinking: Risk Control for Reasoning on a Compute Budget [60.65072883773352]
  Reasoning Large Language Models (LLMs) enable test-time scaling, with dataset-level accuracy improving as the token budget increases.<n>We re-frame the budget setting problem as risk control, limiting the error rate while minimizing compute.<n>Our framework introduces an upper threshold that stops reasoning when the model is confident and a novel lower threshold that preemptively stops unsolvable instances.
  arXiv  Detail & Related papers  (2026-02-03T18:17:22Z)
• SLO-Conditioned Action Routing for Retrieval-Augmented Generation: Objective Ablation and Failure Modes [0.0]
  This work models per- query control as a small discrete action: choose a retrieval depth and a generation mode (guarded vs. auto) or refuse.<n>An offline logged dataset is constructed from SQuAD 2.0 by executing each action and recording accuracy, token cost, hallucination/refusal indicators, and an SLO-weighted reward.<n>Two simple policy-learning objectives are evaluated: supervised classification of the per-state best action and a reward-weighted variant.
  arXiv  Detail & Related papers  (2025-12-27T15:37:53Z)
• The LLM Already Knows: Estimating LLM-Perceived Question Difficulty via Hidden Representations [33.65540900920885]
  Estimating the difficulty of input questions as perceived by large language models (LLMs) is essential for accurate performance evaluation and adaptive inference.<n>We propose a novel approach for difficulty estimation that leverages only the hidden representations produced by the target LLM.
  arXiv  Detail & Related papers  (2025-09-16T09:38:41Z)
• Supervised Optimism Correction: Be Confident When LLMs Are Sure [91.7459076316849]
  We establish a novel theoretical connection between supervised fine-tuning and offline reinforcement learning. We show that the widely used beam search method suffers from unacceptable over-optimism. We propose Supervised Optimism Correction, which introduces a simple yet effective auxiliary loss for token-level $Q$-value estimations.
  arXiv  Detail & Related papers  (2025-04-10T07:50:03Z)
• COPU: Conformal Prediction for Uncertainty Quantification in Natural Language Generation [14.461333001997449]
  Uncertainty Quantification (UQ) for Natural Language Generation (NLG) is crucial for assessing the performance of Large Language Models (LLMs) We propose ourmethod, a method that explicitly adds the ground truth to the candidate outputs and uses logit scores to measure nonconformity.
  arXiv  Detail & Related papers  (2025-02-18T07:25:12Z)
• Assessing Correctness in LLM-Based Code Generation via Uncertainty Estimation [0.0]
  We explore uncertainty estimation as a proxy for correctness in LLM-generated code. We adapt two state-of-the-art techniques from natural language generation to the domain of code generation. Our findings indicate a strong correlation between the uncertainty computed through these techniques and correctness.
  arXiv  Detail & Related papers  (2025-02-17T10:03:01Z)
• Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output [49.893971654861424]
  We present a light-weight approach for detecting nonfactual outputs from retrieval-augmented generation (RAG) We compute a factuality score that can be thresholded to yield a binary decision. Our experiments show high area under the ROC curve (AUC) across a wide range of relevant open source datasets.
  arXiv  Detail & Related papers  (2024-11-01T20:44:59Z)
• CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges [21.580762639442913]
  We introduce CalibraEval, a novel label-free method for mitigating selection bias during inference. CalibraEval reformulates debiasing as an optimization task aimed at adjusting observed prediction distributions to align with unbiased prediction distributions. We show that CalibraEval effectively mitigates selection bias and improves performance compared to existing debiasing methods.
  arXiv  Detail & Related papers  (2024-10-20T13:47:39Z)
• Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification [76.14641982122696]
  We propose a constraint learning schema for fine-tuning Large Language Models (LLMs) with attribute control. We show that our approach leads to an LLM that produces fewer inappropriate responses while achieving competitive performance on benchmarks and a toxicity detection task.
  arXiv  Detail & Related papers  (2024-10-07T23:38:58Z)
• Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization [9.618391485742968]
  Iterative preference optimization has recently become one of the de-facto training paradigms for large language models (LLMs) We present an uncertainty-enhanced textbfPreference textbfOptimization framework to make the LLM self-evolve with reliable feedback. Our framework substantially alleviates the noisy problem and improves the performance of iterative preference optimization.
  arXiv  Detail & Related papers  (2024-09-17T14:05:58Z)
• Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models [104.55763564037831]
  We train a regression model that leverages attention maps, probabilities on the current generation step, and recurrently computed uncertainty scores from previously generated tokens.<n>Our evaluation shows that the proposed method is highly effective for selective generation, achieving substantial improvements over rivaling unsupervised and supervised approaches.
  arXiv  Detail & Related papers  (2024-08-20T09:42:26Z)
• Self-Evaluation Improves Selective Generation in Large Language Models [54.003992911447696]
  We reformulate open-ended generation tasks into token-level prediction tasks. We instruct an LLM to self-evaluate its answers. We benchmark a range of scoring methods based on self-evaluation.
  arXiv  Detail & Related papers  (2023-12-14T19:09:22Z)
• Leaving the Nest: Going Beyond Local Loss Functions for Predict-Then-Optimize [57.22851616806617]
  We show that our method achieves state-of-the-art results in four domains from the literature. Our approach outperforms the best existing method by nearly 200% when the localness assumption is broken.
  arXiv  Detail & Related papers  (2023-05-26T11:17:45Z)
• Balancing Risk and Reward: An Automated Phased Release Strategy [2.1485350418225244]
  Phased releases are a common strategy in the technology industry for gradually releasing new products or updates through a sequence of A/B tests. We propose an algorithm that automatically determines the release percentage at each stage in the schedule, balancing the need to control risk while maximizing ramp-up speed.
  arXiv  Detail & Related papers  (2023-05-16T17:27:34Z)
• Error-based Knockoffs Inference for Controlled Feature Selection [49.99321384855201]
  We propose an error-based knockoff inference method by integrating the knockoff features, the error-based feature importance statistics, and the stepdown procedure together. The proposed inference procedure does not require specifying a regression model and can handle feature selection with theoretical guarantees.
  arXiv  Detail & Related papers  (2022-03-09T01:55:59Z)
• Reinforcement Learning of Risk-Constrained Policies in Markov Decision Processes [5.081241420920605]
  Markov decision processes (MDPs) are the defacto frame-work for sequential decision making in the presence ofstochastic uncertainty. We consider MDPswith discounted-sum payoff with failure states which repre-sent catastrophic outcomes. Our maincontribution is an efficient risk-constrained planning algo-rithm that combines UCT-like search with a predictor learnedthrough interaction with the MDP.
  arXiv  Detail & Related papers  (2020-02-27T13:36:36Z)
• Progressive Identification of True Labels for Partial-Label Learning [112.94467491335611]
  Partial-label learning (PLL) is a typical weakly supervised learning problem, where each training instance is equipped with a set of candidate labels among which only one is the true label. Most existing methods elaborately designed as constrained optimizations that must be solved in specific manners, making their computational complexity a bottleneck for scaling up to big data. This paper proposes a novel framework of classifier with flexibility on the model and optimization algorithm.
  arXiv  Detail & Related papers  (2020-02-19T08:35:15Z)

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.