Guiding LLM to Fool Itself: Automatically Manipulating Machine Reading Comprehension Shortcut Triggers
Comments Accepted to EMNLP 2023 Findings
期刊&会议
Conference on Empirical Methods in Natural Language Processing · 会议 · Natural Language Processing
Comments Accepted to EMNLP 2023 Findings
Comments 12 pages, 5 figures, EMNLP 2023 Long Paper
Comments 9 pages, 4 figures, EMNLP2023 workshop, The 2023 Conference on Empirical Methods in Natural Language Processing
Comments Accepted by Findings of EMNLP 2023, 13 pages
Comments Accepted by the Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. (EMNLP2023)
Comments Accepted for EMNLP-Findings, 2023
Comments 13 pages, 9 figures, 7 tables, accepted to findings of EMNLP 2023
Comments Accepted at EMNLP'2023 Main Conference
Comments EMNLP 2023
Comments EMNLP 2023 Camera-ready, 15 pages
Comments Findings of EMNLP
Comments Accetpted to EMNLP 2023
Comments EMNLP 2023
Comments EMNLP 2023 (main)
Comments Accepted to EMNLP 2023
Comments EMNLP 2023 Main Conference
Comments Accepted to Findings of EMNLP 2023
Comments Findings of EMNLP 2023
Comments Findings of EMNLP 2023
Comments Findings of EMNLP 2023
Comments Accepted to Big Picture workshop at EMNLP 2023
Comments EMNLP 2023 Main Conference, Short Paper
Comments To be published in EMNLP 2023
Comments EMNLP 2023 main paper accepted
Comments Accepted for publication in EMNLP 2023: 13 pages, 3 figures and 14 tables
Comments Accepted to Findings of EMNLP 2023; 10 pages, 5 figures
Comments In EMNLP 2023 main conference proceedings (to appear)
Comments EMNLP Findings 2023
Comments Submitted and rejected by EMNLP 2023. Contact the authors for a copy of the "reviews"
Comments Accepted at GenBench, EMNLP 2023. All authors are co-first authors and have equal contributions