BARS: Budget-Aware Sequential Sampling with Refusal for Majority Identification under Unknown Distributions
cs.AI
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/LtColLiuPeiqiang/adaptive-stopping
Terminology
Sources
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Measuring Mathematical Problem Solving With the MATH Dataset
- Time-uniform, nonparametric, nonasymptotic confidence sequences
- Estimating means of bounded random variables by betting
- Empirical Bernstein Bounds and Sample Variance Penalization
- Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
- Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning
- CGES: Confidence-Guided Early Stopping for Efficient and Accurate Self-Consistency
- Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
- Evaluating Large Language Models Trained on Code
- What Fixed-Rollout pass@k Evaluations Can Identify
- MARS: Margin-Adversarial Risk-controlled Stopping for Parallel LLM Test-time Scaling
- SelectiveNet: A Deep Neural Network with an Integrated Reject Option
- Selective Prediction via Training Dynamics
- Mitigating LLM Hallucinations via Conformal Abstention
- SConU: Selective Conformal Uncertainty in Large Language Models
- When Can Conformal Risk Control Certify LLM Outputs? Bounds, Impossibility, and Adaptation for Structured Generation
- Selective Prediction from Agreement: A Lipschitz-Consistent Version Space Approach
- Certified Self-Consistency: Statistical Guarantees and Test-Time Training for Reliable Reasoning in LLMs
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents