PaperAsk: A Benchmark for Reliability Evaluation of LLMs in Paper Search and Reading.

@inproceedings{wu-2026-paperask, author = {Yutao Wu and Xiao Liu and Yunhao Feng and Jiale Ding and Xingjun Ma}, editor = {Hakim Hacid and Yoelle Maarek and Francesco Bonchi and Ido Guy and Emine Yilmaz}, title = {{PaperAsk: A Benchmark for Reliability Evaluation of LLMs in Paper Search and Reading}}, booktitle = {{Proceedings of the ACM Web Conference 2026, WWW 2026, Dubai, United Arab Emirates, originally scheduled for April 13-17, 2026, rescheduled for June 29 - July 3, 2026}}, pages = {2330--2338}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3774904.3792597}, doi = {https://doi.org/10.1145/3774904.3792597} }