Active Query Synthesis for Preference Learning

• URL: http://arxiv.org/abs/2605.26072v1
• Date: Mon, 25 May 2026 17:37:58 GMT
• Title: Active Query Synthesis for Preference Learning
• Abstract summary: Active learning reduces this cost, yet standard methods are computationally expensive due to pool-based evaluation.<n>We introduce a novel confidence aware response model that explicitly accounts for ambiguous comparisons.<n>We demonstrate our framework's versatility and performance across synthetic preference learning, constrained text summary datasets, and subjective, continuous-space controller gain tuning for a simulated mobile robot.
• Score: 10.489427796755232
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Efficient learning of user preferences is crucial for many modern decision making systems but typically requires costly labeled data. Active learning reduces this cost, yet standard methods are computationally expensive due to pool-based evaluation. Further, most methods assume all query feedback is equally reliable, ignoring that pairwise queries between nearly identical or entirely dissimilar items yield ambiguous, low-confidence responses. To address the issue of feedback reliability, we introduce a novel confidence aware response model that explicitly accounts for these ambiguous comparisons. To overcome the computational bottleneck of pool-based evaluation, we propose an active query synthesis framework, Info-Synth that generates optimal queries by maximizing a mutual information-based objective within a continuous space. Moreover, we propose two strategies, Pair M-dist and Pair Opt-dist, that extend Info-Synth to select effective queries even when restricted to finite query pools. We demonstrate our framework's versatility and performance across synthetic preference learning, constrained text summary datasets, and subjective, continuous-space controller gain tuning for a simulated mobile robot.

Related papers

• Provably Efficient Personalized Multi-Objective Bandits with Proactive Conversational Queries [24.496126767935937]
  We formalize a proactive query-based framework in which user queries provide structured preference signals.<n>We prove that proactive queries accelerate preference estimation and yield improved regret scaling over prior preference-aware MO-MAB methods.
  arXiv  Detail & Related papers  (2026-06-07T02:19:59Z)
• LLM Routing with Dueling Feedback [49.67815163970033]
  We study the problem of selecting the best model for each query while balancing user satisfaction, model expertise, and inference cost.<n>We formulate routing as contextual dueling bandits, learning from pairwise preference feedback rather than absolute scores.<n>We introduce Category-Calibrated Fine-Tuning (CCFT), a representation-learning method that derives model embeddings from offline data using contrastive fine-tuning with categorical weighting.
  arXiv  Detail & Related papers  (2025-10-01T12:52:25Z)
• Semantic Caching for Low-Cost LLM Serving: From Offline Learning to Online Adaptation [54.61034867177997]
  Caching inference responses allows them to be retrieved without another forward pass through the Large Language Models.<n>Traditional exact-match caching overlooks the semantic similarity between queries, leading to unnecessary recomputation.<n>We present a principled, learning-based framework for semantic cache eviction under unknown query and cost distributions.
  arXiv  Detail & Related papers  (2025-08-11T06:53:27Z)
• Embed Progressive Implicit Preference in Unified Space for Deep Collaborative Filtering [13.24227546548424]
  Generalized Neural Ordinal Logistic Regression (GNOLR) is proposed to capture the structured progression of user engagement.<n>GNOLR enhances predictive accuracy, captures the progression of user engagement, and simplifies the retrieval process.<n>Experiments on ten real-world datasets show that GNOLR significantly outperforms state-of-the-art methods in efficiency and adaptability.
  arXiv  Detail & Related papers  (2025-05-27T08:43:35Z)
• Model-Free Counterfactual Subset Selection at Scale [11.646993755965006]
  Streaming explanations offer adaptive, real-time insights without requiring persistent storage of the entire dataset.<n>Our algorithm operates efficiently in streaming settings, maintaining $O(log k)$ update complexity per item.<n> Empirical evaluations on both real-world and synthetic datasets demonstrate superior performance over baseline methods.
  arXiv  Detail & Related papers  (2025-02-12T11:48:15Z)
• A Systematic Examination of Preference Learning through the Lens of Instruction-Following [83.71180850955679]
  We use a novel synthetic data generation pipeline to generate 48,000 instruction unique-following prompts.<n>With our synthetic prompts, we use two preference dataset curation methods - rejection sampling (RS) and Monte Carlo Tree Search (MCTS)<n>Experiments reveal that shared prefixes in preference pairs, as generated by MCTS, provide marginal but consistent improvements.<n>High-contrast preference pairs generally outperform low-contrast pairs; however, combining both often yields the best performance.
  arXiv  Detail & Related papers  (2024-12-18T15:38:39Z)
• Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity [59.57065228857247]
  Retrieval-augmented Large Language Models (LLMs) have emerged as a promising approach to enhancing response accuracy in several tasks, such as Question-Answering (QA) We propose a novel adaptive QA framework, that can dynamically select the most suitable strategy for (retrieval-augmented) LLMs based on the query complexity. We validate our model on a set of open-domain QA datasets, covering multiple query complexities, and show that ours enhances the overall efficiency and accuracy of QA systems.
  arXiv  Detail & Related papers  (2024-03-21T13:52:30Z)
• Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL [62.824464372594576]
  We aim to enhance arithmetic reasoning ability of Large Language Models (LLMs) through zero-shot prompt optimization. We identify a previously overlooked objective of query dependency in such optimization. We introduce Prompt-OIRL, which harnesses offline inverse reinforcement learning to draw insights from offline prompting demonstration data.
  arXiv  Detail & Related papers  (2023-09-13T01:12:52Z)
• HyperImpute: Generalized Iterative Imputation with Automatic Model Selection [77.86861638371926]
  We propose a generalized iterative imputation framework for adaptively and automatically configuring column-wise models. We provide a concrete implementation with out-of-the-box learners, simulators, and interfaces.
  arXiv  Detail & Related papers  (2022-06-15T19:10:35Z)

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.