Efficient Sequential Evaluation of Large Language Models

• URL: http://arxiv.org/abs/2607.17409v1
• Date: Sun, 19 Jul 2026 21:01:34 GMT
• Title: Efficient Sequential Evaluation of Large Language Models
• Abstract summary: We study the problem of sequentially evaluating a new large language model (LLM) on a fixed question set using historical performance data.<n>Our goal is to construct a confidence sequence (CS) for the model's capability on this question set and to design active querying rules that shrink the CS width as quickly as possible.
• Score: 10.520659921457629
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study the problem of sequentially evaluating a new large language model (LLM) on a fixed question set using historical performance data from prior LLMs. Our goal is to construct a confidence sequence (CS) for the model's capability on this question set and to design active querying rules that shrink the CS width as quickly as possible. For CS construction, we invert a family of test supermartingales and focus on two representative approaches: a reverse information projection (RIPr)-based approach and a testing-by-betting-based approach. We first study these approaches under an oracle setting, and demonstrate the oracle optimality of the RIPr-based construction. We then propose a growth-oriented querying rule that aims to maximize the worst-case one-step expected log-increment over the endpoints of the current CS. In practice, we build these test supermartingales and the querying rule on predictions of question-level correctness learned from historical data. We then analyze the shrinkage behavior of the resulting CSs and identify two key factors that slow the shrinkage rate of CSs: accumulated prediction mismatch and the spikiness of the querying distribution. Finally, motivated by this analysis, we propose several mixture querying rules that combine growth-oriented querying, prediction refinement, and uniform exploration, trying to mitigate the effects that slow the shrinkage rate. We provide experiments comparing different querying rules for the RIPr-based and testing-by-betting-based CSs across several synthetic testing datasets. Interestingly, we observe that the simplest querying rule, uniform sampling, can sometimes outperform more adaptive querying rules for both methods.

Related papers

• Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization [20.259122922188126]
  Large Language Models (LLMs) suffer from order bias, where their performance is affected by the arrangement order of input elements.<n>textbfDGAO aims to improve model accuracy and order stability simultaneously.
  arXiv  Detail & Related papers  (2026-05-12T11:31:18Z)
• TopBench: A Benchmark for Implicit Prediction and Reasoning over Tabular Question Answering [80.93487993878836]
  A common class of real-world queries is implicitly predictive, requiring the inference of unobserved answers from historical patterns rather than mere retrieval.<n>These queries introduce two challenges: recognizing latent intent and reliable predictive reasoning over massive tables.<n>We introduce TopBench, a benchmark consisting of 779 samples across four sub-tasks, ranging from single-point prediction to decision making, treatment effect analysis, and complex reasoning.
  arXiv  Detail & Related papers  (2026-04-30T16:22:51Z)
• Retrieve-then-Adapt: Retrieval-Augmented Test-Time Adaptation for Sequential Recommendation [17.159956938670174]
  sequential recommendation (SR) models often struggle to adapt to real-time preference shifts during inference.<n>We propose Retrieve-then-Adapt (ReAd), a novel framework that dynamically adapts a deployed SR model to the test distribution through retrieved user preference signals.<n>Extensive experiments across five benchmark datasets demonstrate that ReAd consistently outperforms existing SR methods.
  arXiv  Detail & Related papers  (2026-04-07T03:24:56Z)
• Precedent-Informed Reasoning: Mitigating Overthinking in Large Reasoning Models via Test-Time Precedent Learning [37.40951956513094]
  Reasoning in Large Language Models (LLMs) often suffers from inefficient long chain-of-thought traces with redundant self-exploration and validation.<n>Inspired by human reasoning patterns where people solve new problems by leveraging past related cases to constrain search spaces and reduce trial-and-error, we propose Precedent Informed Reasoning (PIR)<n>PIR transforms LRMs'reasoning paradigm from exhaustive self-exploration to guided learning from precedents.
  arXiv  Detail & Related papers  (2026-02-16T04:17:46Z)
• Conformal Information Pursuit for Interactively Guiding Large Language Models [68.16703423481935]
  This paper explores sequential querying strategies that aim to minimize the expected number of queries.<n>One such strategy is Information Pursuit (IP), a greedy algorithm that at each iteration selects the query that maximizes information gain or equivalently minimizes uncertainty.<n>We propose Conformal Information Pursuit (C-IP), an alternative approach to sequential information gain based on conformal prediction sets.
  arXiv  Detail & Related papers  (2025-07-04T03:55:39Z)
• Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models [20.810300785340072]
  Conformal Prediction with Query Oracle (CPQ) is a framework characterizing the optimal interplay between these objectives.<n>Our algorithm is built on two core principles: one governs the optimal query policy, and the other defines the optimal mapping from queried samples to prediction sets.
  arXiv  Detail & Related papers  (2025-06-05T18:26:14Z)
• TACO: Think-Answer Consistency for Optimized Long-Chain Reasoning and Efficient Data Learning via Reinforcement Learning in LVLMs [50.820065021136024]
  DeepSeek R1 has significantly advanced complex reasoning for large language models (LLMs)<n>Recent methods have attempted to replicate R1's reasoning capabilities in multimodal settings.<n>We propose TACO, a novel reinforcement learning algorithm for visual reasoning.
  arXiv  Detail & Related papers  (2025-05-27T06:30:48Z)
• Chain-of-Retrieval Augmented Generation [91.02950964802454]
  This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer.<n>Our proposed method, CoRAG, allows the model to dynamically reformulate the query based on the evolving state.
  arXiv  Detail & Related papers  (2025-01-24T09:12:52Z)
• Progressive End-to-End Object Detection in Crowded Scenes [96.92416613336096]
  Previous query-based detectors suffer from two drawbacks: first, multiple predictions will be inferred for a single object, typically in crowded scenes; second, the performance saturates as the depth of the decoding stage increases. We propose a progressive predicting method to address the above issues. Specifically, we first select accepted queries to generate true positive predictions, then refine the rest noisy queries according to the previously accepted predictions. Experiments show that our method can significantly boost the performance of query-based detectors in crowded scenes.
  arXiv  Detail & Related papers  (2022-03-15T06:12:00Z)
• Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoning [61.32992639292889]
  Fine-tuning of pre-trained transformer models has become the standard approach for solving common NLP tasks. We introduce a new scoring method that casts a plausibility ranking task in a full-text format. We show that our method provides a much more stable training phase across random restarts.
  arXiv  Detail & Related papers  (2020-04-29T10:54:40Z)

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.