用作者回复优化AI反馈，让论文修改建议更实用有效
GoodPoint: Learning Constructive Scientific Paper Feedback from Author Responses
- 基于作者回复构建反馈有效性与可操作性双维度标注
- 训练模型使反馈匹配度提升83.7%，超越同规模模型
- 适合希望提升论文修改效率的研究者使用
尽管大模型在科学科研中潜力巨大，我们主张其应辅助研究者而非完全替代人工。为此，本文研究建设性反馈生成任务，即提供有针对性、可执行的反馈以帮助作者改进研究与表述。我们从两个以作者为中心的维度衡量反馈效果：有效性与作者行动性。首先构建了包含19,000篇ICLR论文的GoodPoint-ICLR数据集，利用作者回复对反馈进行双维度标注。在此基础上，提出GoodPoint训练方案，通过微调有效且可操作的反馈，并结合真实与合成偏好对进行偏好优化。在1,200篇ICLR论文的基准测试中，经GoodPoint训练的Qwen3-8B相比基线模型预测成功率提升83.7%，在黄金人类反馈集上达到同类模型新高，甚至优于Gemini-3-flash的精确率。专家人工评估进一步验证，作者普遍认为GoodPoint反馈更具实际价值。
原文摘要 · Abstract (English)
While LLMs hold significant potential to transform scientific research, we advocate for their use to augment and empower researchers rather than to automate research without human oversight. To this end, we study constructive feedback generation, the task of producing targeted, actionable feedback that helps authors improve both their research and its presentation. In this work, we operationalize the effectiveness of feedback along two author-centric axes-validity and author action. We first curate GoodPoint-ICLR, a dataset of 19K ICLR papers with reviewer feedback annotated along both dimensions using author responses. Building on this, we introduce GoodPoint, a training recipe that leverages success signals from author responses through fine-tuning on valid and actionable feedback, together with preference optimization on both real and synthetic preference pairs. Our evaluation on a benchmark of 1.2K ICLR papers shows that a GoodPoint-trained Qwen3-8B improves the predicted success rate by 83.7% over the base model and sets a new state-of-the-art among LLMs of similar size in feedback matching on a golden human feedback set, even surpassing Gemini-3-flash in precision. We further validate these findings through an expert human study, demonstrating that GoodPoint consistently delivers higher practical value as perceived by authors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。