{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T03:19:33Z","timestamp":1778901573637,"version":"3.51.4"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10825537","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"1243-1248","source":"Crossref","is-referenced-by-count":7,"title":["Zero-shot LLM-guided Counterfactual Generation: A Case Study on NLP Model Evaluation"],"prefix":"10.1109","author":[{"given":"Amrita","family":"Bhattacharjee","sequence":"first","affiliation":[{"name":"Arizona State University,School of Computing and AI,Tempe,AZ,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raha","family":"Moraffah","sequence":"additional","affiliation":[{"name":"Worcester Polytechnic Institute,Department of Computer Science,Worcester,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joshua","family":"Garland","sequence":"additional","affiliation":[{"name":"Arizona State University,Global Security Initiative,Tempe,AZ,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huan","family":"Liu","sequence":"additional","affiliation":[{"name":"Arizona State University,School of Computing and AI,Tempe,AZ,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Interpretable machine learning","author":"Molnar","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.523"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17594"},{"key":"ref4","article-title":"Towards llm-guided causal explainability for black-box text classifiers","volume-title":"AAAI 2024 Workshop on Responsible Language Models","author":"Bhattacharjee"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.117"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1509"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.306"},{"key":"ref8","article-title":"Plug and play counterfactual text generation for model robustness","author":"Madaan","year":"2022"},{"key":"ref9","first-page":"13201","article-title":"Prompting large language models for counterfactual generation: An empirical study","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)","author":"Li"},{"key":"ref10","first-page":"2303","article-title":"Gpt-4 technical report","year":"2023","journal-title":"arXiv"},{"key":"ref11","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref12","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref13","article-title":"Gemini: a family of highly capable multimodal models","author":"Anil","year":"2023"},{"key":"ref14","article-title":"The refinedweb dataset for falcon llm: Outperforming curated corpora with web data, and web data only","author":"Penedo","year":"2023","journal-title":"CoRR"},{"key":"ref15","article-title":"The pile: An 800gb dataset of diverse text for language modeling","author":"Gao","year":"2020"},{"key":"ref16","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"70","key":"ref17","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"JMLR"},{"key":"ref18","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Sparks of artificial general intelligence: Early experiments with gpt-4","author":"Bubeck","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2305016120"},{"key":"ref22","first-page":"142","article-title":"Learning word vectors for sentiment analysis","volume-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies","author":"Maas"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3115\/1599081.1599147"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1075"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.263"},{"key":"ref27","article-title":"e-snli: Natural language inference with natural language explanations","volume":"31","author":"Camburu","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","article-title":"Learning the difference that makes a difference with counterfactually-augmented data","volume-title":"ICLR","author":"Kaushik"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.12"},{"key":"ref30","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.498"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.442"},{"key":"ref33","article-title":"Scaling language models: Methods, analysis & insights from training gopher","author":"Rae","year":"2021"},{"key":"ref34","article-title":"Large language models still can\u2019t plan (a benchmark for llms on planning and reasoning about change)","volume-title":"NeurIPS 2022 FMDM Workshop","author":"Valmeekam"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","location":"Washington, DC, USA","start":{"date-parts":[[2024,12,15]]},"end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10825537.pdf?arnumber=10825537","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:47:14Z","timestamp":1737100034000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10825537\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10825537","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}