From Coarse to Fine: Benchmarking and Reward Modeling for Writing-Centric Generation Tasks

• URL: http://arxiv.org/abs/2604.27453v1
• Date: Thu, 30 Apr 2026 05:49:29 GMT
• Title: From Coarse to Fine: Benchmarking and Reward Modeling for Writing-Centric Generation Tasks
• Abstract summary: Large language models have achieved remarkable progress in text generation but still struggle with generative writing tasks.<n>We propose a fine-grained evaluation pipeline WEval for writing reward models and a fine-grained reinforcement learning training framework WRL.<n>WRL constructs positive and negative samples by selectively dropping instruction requirements, allowing for more precise reward model training.
• Score: 2.2483228605450956
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models have achieved remarkable progress in text generation but still struggle with generative writing tasks. In terms of evaluation, existing benchmarks evaluate writing reward models coarsely and fail to measure performance from the perspective of specific requirements. In terms of training, existing training methods either use LLM-as-a-judge approaches or train coarse-grained reward models, lacking fine-grained requirement-adherence reward modeling. To address these issues, we propose a fine-grained evaluation pipeline WEval for writing reward models and a fine-grained reinforcement learning training framework WRL. The evaluation data of WEval covers multiple task categories and requirement types, enabling systematic evaluation of writing reward models by measuring the correlation between the rankings of the reward model and gold rankings. WRL constructs positive and negative samples by selectively dropping instruction requirements, allowing for more precise reward model training. Experiments show that our models achieve substantial improvements across various writing benchmarks and exhibit strong generalization. The code and data are publicly available at \href{https://github.com/Rainier-rq1/From_Coarse_to_Fine}{https://github.com/Rainier-rq1/From\_Coarse\_to\_Fine}.

Related papers

• RubricRM: Generative Reward Modeling via Dynamic Rubrics for Image Generation and Editing [9.858046310638803]
  We propose a pairwise generative reward modeling framework that produces an input-specific rubric with evaluation dimensions, weights, and scoring criteria, and then applies the rubric to score candidate images.<n>We train dedicatedRM models for text-to-image generation and image editing using a two-stage training pipeline: supervised fine-tuning teaches the model the model the rubric-based scoring, while further improves scoring through fine-level rewards.
  arXiv  Detail & Related papers  (2026-08-27T10:56:47Z)
• Expected Value Alignment for Generative Reward Modeling in Formal Mathematics Verification [12.08180258890855]
  We introduce Expected Value Alignment (EVA), a reward-modeling procedure that keeps the surface output discrete while extracting continuous scores from the model's token distribution.<n>We instantiate EVA in textitLeibniz, a reward model for Lean 4 formal verification, and evaluate it against zero-shot and reward-modeling baselines.
  arXiv  Detail & Related papers  (2026-05-31T11:06:48Z)
• RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time [51.256131853751754]
  We show that teaching reward models to produce explicit, multi-dimensional critiques transforms them from passive evaluators into active optimization tools.<n>We introduce Preference-Anchored Rationalization (PARROT), a principled framework that recovers high-quality rationales from readily available preference data.<n>The resulting model, RationalRewards (8B), achieves state-of-the-art preference prediction among open-source reward models.
  arXiv  Detail & Related papers  (2026-04-13T15:38:09Z)
• Smaller Models, Smarter Rewards: A Two-Sided Approach to Process and Outcome Rewards [40.23960862004138]
  This paper investigates whether state-of-the-art small language models can be turned into usable reward models.<n>We construct a dataset of code samples with correctness labels derived from the APPS coding challenge benchmark.<n>Using this critic, we achieve over a 20% improvement in the search capability of the most accurate code out of multiple generations.
  arXiv  Detail & Related papers  (2025-10-27T07:36:41Z)
• GRAM: A Generative Foundation Reward Model for Reward Generalization [48.63394690265176]
  We develop a generative reward model that is first trained via large-scale unsupervised learning and then fine-tuned via supervised learning.<n>This model generalizes well across several tasks, including response ranking, reinforcement learning from human feedback, and task adaptation with fine-tuning.
  arXiv  Detail & Related papers  (2025-06-17T04:34:27Z)
• Intra-Trajectory Consistency for Reward Modeling [67.84522106537274]
  We develop an intra-trajectory consistency regularization to enforce that adjacent processes with higher next-token generation probability maintain more consistent rewards.<n>We show that the reward model trained with the proposed regularization induces better DPO-aligned policies and achieves better best-of-N (BON) inference-time verification results.
  arXiv  Detail & Related papers  (2025-06-10T12:59:14Z)
• RewardBench 2: Advancing Reward Model Evaluation [71.65938693914153]
  Reward models are used throughout the post-training of language models to capture nuanced signals from preference data.<n>The community has begun establishing best practices for evaluating reward models.<n>This paper introduces RewardBench 2, a new multi-skill reward modeling benchmark.
  arXiv  Detail & Related papers  (2025-06-02T17:54:04Z)
• RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution [50.171320156632866]
  Reinforcement learning from human feedback offers a promising approach to aligning large language models with human preferences.<n>Current reward models operate as sequence-to-one models, allocating a single, sparse, and delayed reward to an entire output sequence.<n>We propose a more fine-grained, token-level guidance approach for RL training.
  arXiv  Detail & Related papers  (2024-11-13T02:45:21Z)
• RewardBench: Evaluating Reward Models for Language Modeling [100.28366840977966]
  We present RewardBench, a benchmark dataset and code-base for evaluation of reward models. The dataset is a collection of prompt-chosen-rejected trios spanning chat, reasoning, and safety. On the RewardBench leaderboard, we evaluate reward models trained with a variety of methods.
  arXiv  Detail & Related papers  (2024-03-20T17:49:54Z)

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.