Preference Optimization for Review Question Generation Improves Writing Quality

• URL: http://arxiv.org/abs/2602.15849v1
• Date: Fri, 23 Jan 2026 18:58:22 GMT
• Title: Preference Optimization for Review Question Generation Improves Writing Quality
• Authors: Karun Sharma, Vidushee Vats, Shengzhi Li, Yuxiang Wang, Zhongtian Sun, Prayag Tiwari,
• Abstract summary: We develop a novel reward model built from a frozen autoregressive LLM with trainable multi-head transformers.<n>We train a question-generation model aligned with human standards of effort, evidence, and grounding.<n>Compared to the Qwen3-32B base model, IntelliAsk shows measurable gains across diverse benchmarks.
• Score: 29.997337923485933
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Peer review relies on substantive, evidence-based questions, yet existing LLM-based approaches often generate surface-level queries, drawing over 50\% of their question tokens from a paper's first page. To bridge this gap, we develop IntelliReward, a novel reward model built from a frozen autoregressive LLM with trainable multi-head transformers over the final 50 token states, which outperforms API-based SFT baselines in predicting expert-level human preferences. By applying Decoupled Clip and Dynamic Sampling Policy Optimization (DAPO) with IntelliReward, we train IntelliAsk, a question-generation model aligned with human standards of effort, evidence, and grounding. We find consistent improvements on reasoning and writing benchmarks, suggesting reviewer-question quality correlates with broader capabilities. Compared to the Qwen3-32B base model, IntelliAsk shows measurable gains across diverse benchmarks, specifically improving performance on reasoning tasks like MuSR (68.3 vs 64.7 Acc) and complex writing evaluations such as WritingBench (8.31 vs 8.07). We release our implementation, expert preference annotations, and the IntelliReward model to provide an automatic evaluation benchmark for grounding, effort, and evidence in LLM-generated review questions.

Related papers

• Evaluating from Benign to Dynamic Adversarial: A Squid Game for Large Language Models [57.33350664910483]
  We introduce Squid Game, a dynamic and adversarial evaluation environment with resource-constrained and asymmetric information settings.<n>We evaluate over 50 LLMs on Squid Game, presenting the largest behavioral evaluation study of general LLMs on dynamic adversarial scenarios.
  arXiv  Detail & Related papers  (2025-11-12T06:06:29Z)
• Automated Refinement of Essay Scoring Rubrics for Language Models via Reflect-and-Revise [41.16092952642748]
  This study investigates the potential for enhancing Automated Scoring (AES) by refining rubrics used by Large Language Models (LLMs)<n> Experiments on datasets using GPT-4.1, Gemini-2.5-Pro, and Qwen-3-Next-80B-A3B-Instruct show Quadratic Weighted Kappa (QWK) improvements of up to 0.19 and 0.47, respectively.
  arXiv  Detail & Related papers  (2025-10-10T06:05:38Z)
• MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization [103.74675519953898]
  Long-chain reflective reasoning is a prerequisite for solving complex real-world problems.<n>We build a benchmark consisting 1,260 samples of 42 challenging synthetic tasks.<n>We generate post-training data and explore learning paradigms for exploiting such data.
  arXiv  Detail & Related papers  (2025-10-09T17:53:58Z)
• SPELL: Self-Play Reinforcement Learning for evolving Long-Context Language Models [79.01078135582127]
  SPELL enables scalable, label-free optimization for long-context reasoning.<n>We introduce an automated curriculum that gradually increases document length and a reward function that adapts question difficulty to the model's evolving capabilities.
  arXiv  Detail & Related papers  (2025-09-28T13:08:10Z)
• Discriminative Policy Optimization for Token-Level Reward Models [55.98642069903191]
  Process reward models (PRMs) provide more nuanced supervision compared to outcome reward models (ORMs)<n>Q-RM explicitly learns token-level Q-functions from preference data without relying on fine-grained annotations.<n>Reinforcement learning with Q-RM significantly enhances training efficiency, achieving convergence 12 times faster than ORM on GSM8K and 11 times faster than step-level PRM on MATH.
  arXiv  Detail & Related papers  (2025-05-29T11:40:34Z)
• SCAN: Structured Capability Assessment and Navigation for LLMs [54.54085382131134]
  textbfSCAN (Structured Capability Assessment and Navigation) is a practical framework that enables detailed characterization of Large Language Models.<n>SCAN incorporates four key components:.<n>TaxBuilder, which extracts capability-indicating tags from queries to construct a hierarchical taxonomy;.<n>RealMix, a query synthesis and filtering mechanism that ensures sufficient evaluation data for each capability tag;.<n>A PC$2$-based (Pre-Comparison-derived Criteria) LLM-as-a-Judge approach achieves significantly higher accuracy compared to classic LLM-as-a-Judge method
  arXiv  Detail & Related papers  (2025-05-10T16:52:40Z)
• AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security [74.22452069013289]
  AegisLLM is a cooperative multi-agent defense against adversarial attacks and information leakage.<n>We show that scaling agentic reasoning system at test-time substantially enhances robustness without compromising model utility.<n> Comprehensive evaluations across key threat scenarios, including unlearning and jailbreaking, demonstrate the effectiveness of AegisLLM.
  arXiv  Detail & Related papers  (2025-04-29T17:36:05Z)
• YourBench: Easy Custom Evaluation Sets for Everyone [12.995134931278056]
  YourBench is a novel, open-source framework for evaluating large language models (LLMs)<n>It generates reliable, up-to-date, and domain-tailored benchmarks cheaply and without manual annotation.<n>We release the YourBench library, the Tempora-0325 dataset, 150k+ question answer pairs based on Tempora and all evaluation and inference traces.
  arXiv  Detail & Related papers  (2025-04-02T15:40:24Z)
• Self-Taught Evaluators [77.92610887220594]
  We present an approach that aims to im-proves without human annotations, using synthetic training data only. Our Self-Taught Evaluator can improve a strong LLM from 75.4 to 88.3 on RewardBench.
  arXiv  Detail & Related papers  (2024-08-05T17:57:02Z)
• MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs [55.20845457594977]
  Large language models (LLMs) have shown increasing capability in problem-solving and decision-making.<n>We present a process-based benchmark MR-Ben that demands a meta-reasoning skill.<n>Our meta-reasoning paradigm is especially suited for system-2 slow thinking.
  arXiv  Detail & Related papers  (2024-06-20T03:50:23Z)
• Enhancing Large Language Model Performance To Answer Questions and Extract Information More Accurately [2.1715455600756646]
  Large Language Models (LLMs) generate responses to questions. Their effectiveness is often hindered by sub-optimal quality of answers and occasional failures to provide accurate responses to questions. To address these challenges, a fine-tuning process is employed, involving feedback and examples to refine models.
  arXiv  Detail & Related papers  (2024-01-27T00:18:07Z)

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.