Ziyu Chen, Yilun Zhao, Chengye Wang, Rilyn R. Han, Manasi Patwardhan, Arman Cohan. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Sihong Wu, Owen Jiang, Yilun Zhao, Tiansheng Hu, Yiling Ma, Kaiyan Zhang, Manasi Patwardhan, Arman Cohan. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Yilun Zhao, Weiyuan Chen, Zhijian Xu, Manasi Patwardhan, Chengye Wang, Yixin Liu, Lovekesh Vig, Arman Cohan. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Aniketh Garikaparthi, Manasi Patwardhan, Aditya Sanjiv Kanade, Aman Hassan, Lovekesh Vig, Arman Cohan. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Peer review is fundamental to scientific research, but the growing volume of publications has intensified the challenges of this expertise-intensive process. While LLMs show promise in various scientific tasks, their potential to assist with peer review, particularly in identifying paper limitations, remains understudied. We first present a comprehensive taxonomy of limitation types in scientific research, with a focus on AI. Guided by this taxonomy, for studying limitations, we present LimitGen, the first comprehensive benchmark for evaluating LLMs’ capability to support early-stage feedback and complement human peer review. Our benchmark consists of two subsets: LimitGen-Syn, a synthetic dataset carefully created through controlled perturbations of high-quality papers, and LimitGen-Human, a collection of real human-written limitations. To improve the ability of LLM systems to identify limitations, we augment them with literature retrieval, which is essential for grounding identifying limitations in prior scientific findings. Our approach enhances the capabilities of LLM systems to generate limitations in research papers, enabling them to provide more concrete and constructive feedback.

We consider a task based on CVPR 2018 challenge dataset on advertisement (Ad) understanding.The task involves detecting the viewer's interpretation of an Ad image captured as text.Recent results have shown that the embedded scene-text in the image holds a vital cue for this task.Motivated by this, we fine-tune the base BERT model for a sentencepair classification task.Despite utilizing the scene-text as the only source of visual information, we could achieve a hit-or-miss accuracy of 84.95% on the challenge test data.To enable BERT to process other visual information, we append image captions to the scene-text.This achieves an accuracy of 89.69%, which is an improvement of 4.7%.This is the best reported result for this task.

Compliant software is a critical need of all modern businesses. Disambiguating regulations to derive requirements is therefore an important software engineering activity. Regulations however are ridden with ambiguities that make their comprehension a challenge, seemingly surmountable only by legal experts. Since legal experts' involvement in every project is expensive, approaches to automate the disambiguation need to be explored. These approaches however require a large amount of annotated data. Collecting data exclusively from experts is not a scalable and affordable solution. In this paper, we present the results of a crowd sourcing experiment to collect annotations on ambiguities in regulations from professional software engineers. We discuss an approach to automate the arduous and critical step of identifying ground truth labels by employing crowd consensus using Expectation Maximization (EM). We demonstrate that the annotations reaching a consensus match those of experts with an accuracy of 87%.