Graham Neubig

On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists

人工智能审稿人的局限与机遇：对Nature系列论文审稿的45位专家科学家的审查

Seungone Kim, Dongkeun Yoon, Kiril Gashteovski, Juyoung Suk, Jinheon Baek, Pranjal Aggarwal, Ian Wu, Viktor Zaverkin, Spase Petkoski, Daniel R. Schrider, Ilija Dukovski, Francesco Santini, Biljana Mitreska, Yong Jeong, Kyeongha Kwon, Young Min Sim, Dragana Manasova, Arthur Porto, Biljana Mojsoska, Makoto Takamoto, Marko Shuntov, Ruoqi Liu, Hyunjoo Jenny Lee, Niyazi Ulas Dinç, Yehhyun Jo, Sunkyu Han, Chungwoo Lee, Huishan Li, Esther H. R. Tsai, Ergun Simsek, Khushboo Shafi, Yeonseung Chung, Jihye Park, Aleksandar Shulevski, Henrik Christiansen, Yoosang Son, Elly Knight, Amanda Montoya, Jeongyoun Ahn, Christian Langkammer, Heera Moon, Changwon Yoon, Nikola Stikov, Mooseok Jang, Edward Choi, Junhan Kim, Yeon Sik Jung, Woo Youn Kim, Jae Kyoung Kim, Ishraq Md Anjum, Hyun Uk Kim, Drew Bridges, Carolin Lawrence, Xiang Yue, Alice Oh, Akari Asai, Sean Welleck, Graham Neubig

机构 * Nature（自然） 纠错

AI总结 本文通过大规模专家标注研究，探讨了AI审稿人在科学同行评审中的能力与局限，发现AI审稿在准确性、显著性和证据充分性方面表现优异，但存在领域知识有限、上下文管理不足等弱点，表明AI审稿是人类审稿的补充而非替代。

Comments Work in progress

Reinforcing Human Behavior Simulation via Verbal Feedback

通过言语反馈强化人类行为模拟

Weiwei Sun, Xuhui Zhou, Jiarui Liu, Weihua Du, Haojia Sun, Yiqing Xie, Qianou Ma, Sihao Chen, Mengting Wan, Longqi Yang, Pei Zhou, Sherry Wu, Sean Welleck, Graham Neubig, Yiming Yang, Maarten Sap

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Microsoft（微软） 纠错

AI总结 本文提出DITTO模型，通过将言语反馈作为强化学习中的首要信号来提升LLM模拟人类行为的能力，并引入SOUL基准测试平台，展示了在多个任务中显著提升性能的成果。