The Sixth Workshop on Insights from Negative Results in NLP

The Sixth Workshop on Insights from Negative Results in NLP Aleksandr Drozd editor João Sedoc editor Shabnam Tafreshi editor Arjun Akula editor Raphael Shu editor 2025-05 Association for Computational Linguistics Albuquerque, New Mexico text conference publication 979-8-89176-240-4 insights-ws-2025-1 10.18653/v1/2025.insights-1.0 https://aclanthology.org/2025.insights-1.0/ Challenging Assumptions in Learning Generic Text Style Embeddings Phil Ostheimer author Marius Kloft author Sophie Fellenz author 2025-05 text The Sixth Workshop on Insights from Negative Results in NLP Aleksandr Drozd editor João Sedoc editor Shabnam Tafreshi editor Arjun Akula editor Raphael Shu editor Association for Computational Linguistics Albuquerque, New Mexico conference publication 979-8-89176-240-4 ostheimer-etal-2025-challenging 10.18653/v1/2025.insights-1.1 https://aclanthology.org/2025.insights-1.1/ 2025-05 1 6 In-Context Learning on a Budget: A Case Study in Token Classification Uri Berger author Tal Baumel author Gabriel Stanovsky author 2025-05 text The Sixth Workshop on Insights from Negative Results in NLP Aleksandr Drozd editor João Sedoc editor Shabnam Tafreshi editor Arjun Akula editor Raphael Shu editor Association for Computational Linguistics Albuquerque, New Mexico conference publication 979-8-89176-240-4 berger-etal-2025-context 10.18653/v1/2025.insights-1.2 https://aclanthology.org/2025.insights-1.2/ 2025-05 7 14 Reassessing Graph Linearization for Sequence-to-sequence AMR Parsing: On the Advantages and Limitations of Triple-Based Jeongwoo Kang author Maximin Coavoux author Didier Schwab author Cédric Lopez author 2025-05 text The Sixth Workshop on Insights from Negative Results in NLP Aleksandr Drozd editor João Sedoc editor Shabnam Tafreshi editor Arjun Akula editor Raphael Shu editor Association for Computational Linguistics Albuquerque, New Mexico conference publication 979-8-89176-240-4 kang-etal-2025-reassessing 10.18653/v1/2025.insights-1.3 https://aclanthology.org/2025.insights-1.3/ 2025-05 15 23 Corrective In-Context Learning: Evaluating Self-Correction in Large Language Models Mario Sanz-Guerrero author Katharina von der Wense author 2025-05 text The Sixth Workshop on Insights from Negative Results in NLP Aleksandr Drozd editor João Sedoc editor Shabnam Tafreshi editor Arjun Akula editor Raphael Shu editor Association for Computational Linguistics Albuquerque, New Mexico conference publication 979-8-89176-240-4 s-a-n-z-g-u-e-r-r-e-r-o-von-der-wense-2025-corrective 10.18653/v1/2025.insights-1.4 https://aclanthology.org/2025.insights-1.4/ 2025-05 24 33 Do Prevalent Bias Metrics Capture Allocational Harms from LLMs? Hannah Cyberey author Yangfeng Ji author David Evans author 2025-05 text The Sixth Workshop on Insights from Negative Results in NLP Aleksandr Drozd editor João Sedoc editor Shabnam Tafreshi editor Arjun Akula editor Raphael Shu editor Association for Computational Linguistics Albuquerque, New Mexico conference publication 979-8-89176-240-4 cyberey-etal-2025-prevalent 10.18653/v1/2025.insights-1.5 https://aclanthology.org/2025.insights-1.5/ 2025-05 34 45 Language-Specific Neurons Do Not Facilitate Cross-Lingual Transfer Soumen Kumar Mondal author Sayambhu Sen author Abhishek Singhania author Preethi Jyothi author 2025-05 text The Sixth Workshop on Insights from Negative Results in NLP Aleksandr Drozd editor João Sedoc editor Shabnam Tafreshi editor Arjun Akula editor Raphael Shu editor Association for Computational Linguistics Albuquerque, New Mexico conference publication 979-8-89176-240-4 mondal-etal-2025-language 10.18653/v1/2025.insights-1.6 https://aclanthology.org/2025.insights-1.6/ 2025-05 46 62 Monte Carlo Sampling for Analyzing In-Context Examples Stephanie Schoch author Yangfeng Ji author 2025-05 text The Sixth Workshop on Insights from Negative Results in NLP Aleksandr Drozd editor João Sedoc editor Shabnam Tafreshi editor Arjun Akula editor Raphael Shu editor Association for Computational Linguistics Albuquerque, New Mexico conference publication 979-8-89176-240-4 schoch-ji-2025-monte 10.18653/v1/2025.insights-1.7 https://aclanthology.org/2025.insights-1.7/ 2025-05 63 78 Does Training on Synthetic Data Make Models Less Robust? Lingze Zhang author Ellie Pavlick author 2025-05 text The Sixth Workshop on Insights from Negative Results in NLP Aleksandr Drozd editor João Sedoc editor Shabnam Tafreshi editor Arjun Akula editor Raphael Shu editor Association for Computational Linguistics Albuquerque, New Mexico conference publication 979-8-89176-240-4 zhang-pavlick-2025-training 10.18653/v1/2025.insights-1.8 https://aclanthology.org/2025.insights-1.8/ 2025-05 79 85 Bridging the Faithfulness Gap in Prototypical Models Andrew Koulogeorge author Sean Xie author Saeed Hassanpour author Soroush Vosoughi author 2025-05 text The Sixth Workshop on Insights from Negative Results in NLP Aleksandr Drozd editor João Sedoc editor Shabnam Tafreshi editor Arjun Akula editor Raphael Shu editor Association for Computational Linguistics Albuquerque, New Mexico conference publication 979-8-89176-240-4 koulogeorge-etal-2025-bridging 10.18653/v1/2025.insights-1.9 https://aclanthology.org/2025.insights-1.9/ 2025-05 86 99 Aligning Sizes of Intermediate Layers by LoRA Adapter for Knowledge Distillation Takeshi Suzuki author Hiroaki Yamada author Takenobu Tokunaga author 2025-05 text The Sixth Workshop on Insights from Negative Results in NLP Aleksandr Drozd editor João Sedoc editor Shabnam Tafreshi editor Arjun Akula editor Raphael Shu editor Association for Computational Linguistics Albuquerque, New Mexico conference publication 979-8-89176-240-4 suzuki-etal-2025-aligning 10.18653/v1/2025.insights-1.10 https://aclanthology.org/2025.insights-1.10/ 2025-05 100 105 LLMs are not Zero-Shot Reasoners for Biomedical Information Extraction Aishik Nagar author Viktor Schlegel author Thanh-Tung Nguyen author Hao Li author Yuping Wu author Kuluhan Binici author Stefan Winkler author 2025-05 text The Sixth Workshop on Insights from Negative Results in NLP Aleksandr Drozd editor João Sedoc editor Shabnam Tafreshi editor Arjun Akula editor Raphael Shu editor Association for Computational Linguistics Albuquerque, New Mexico conference publication 979-8-89176-240-4 nagar-etal-2025-llms 10.18653/v1/2025.insights-1.11 https://aclanthology.org/2025.insights-1.11/ 2025-05 106 120 Exploring Limitations of LLM Capabilities with Multi-Problem Evaluation Zhengxiang Wang author Jordan Kodner author Owen Rambow author 2025-05 text The Sixth Workshop on Insights from Negative Results in NLP Aleksandr Drozd editor João Sedoc editor Shabnam Tafreshi editor Arjun Akula editor Raphael Shu editor Association for Computational Linguistics Albuquerque, New Mexico conference publication 979-8-89176-240-4 wang-etal-2025-exploring 10.18653/v1/2025.insights-1.12 https://aclanthology.org/2025.insights-1.12/ 2025-05 121 140 Exploring Multimodal Language Models for Sustainability Disclosure Extraction: A Comparative Study Tanay Gupta author Tushar Goel author Ishan Verma author 2025-05 text The Sixth Workshop on Insights from Negative Results in NLP Aleksandr Drozd editor João Sedoc editor Shabnam Tafreshi editor Arjun Akula editor Raphael Shu editor Association for Computational Linguistics Albuquerque, New Mexico conference publication 979-8-89176-240-4 gupta-etal-2025-exploring 10.18653/v1/2025.insights-1.13 https://aclanthology.org/2025.insights-1.13/ 2025-05 141 149 Self Knowledge-Tracing for Tool Use (SKT-Tool): Helping LLM Agents Understand Their Capabilities in Tool Use Joshua Vigel author Renpei Cai author Eleanor Chen author Anish Neema author Austen Liao author Kevin Zhu author Sean O’brien author 2025-05 text The Sixth Workshop on Insights from Negative Results in NLP Aleksandr Drozd editor João Sedoc editor Shabnam Tafreshi editor Arjun Akula editor Raphael Shu editor Association for Computational Linguistics Albuquerque, New Mexico conference publication 979-8-89176-240-4 vigel-etal-2025-self 10.18653/v1/2025.insights-1.14 https://aclanthology.org/2025.insights-1.14/ 2025-05 150 156 Error Reflection Prompting: Can Large Language Models Successfully Understand Errors? Jason Li author Lauren Yraola author Kevin Zhu author Sean O’brien author 2025-05 text The Sixth Workshop on Insights from Negative Results in NLP Aleksandr Drozd editor João Sedoc editor Shabnam Tafreshi editor Arjun Akula editor Raphael Shu editor Association for Computational Linguistics Albuquerque, New Mexico conference publication 979-8-89176-240-4 li-etal-2025-error 10.18653/v1/2025.insights-1.15 https://aclanthology.org/2025.insights-1.15/ 2025-05 157 170 Evaluating Robustness of LLMs to Numerical Variations in Mathematical Reasoning Yuli Yang author Hiroaki Yamada author Takenobu Tokunaga author 2025-05 text The Sixth Workshop on Insights from Negative Results in NLP Aleksandr Drozd editor João Sedoc editor Shabnam Tafreshi editor Arjun Akula editor Raphael Shu editor Association for Computational Linguistics Albuquerque, New Mexico conference publication 979-8-89176-240-4 yang-etal-2025-evaluating 10.18653/v1/2025.insights-1.16 https://aclanthology.org/2025.insights-1.16/ 2025-05 171 180