{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T05:07:20Z","timestamp":1737176840453,"version":"3.33.0"},"reference-count":37,"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\/bigdata62323.2024.10825408","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"5289-5297","source":"Crossref","is-referenced-by-count":0,"title":["Adversarially Exploring Vulnerabilities in LLMs to Evaluate Social Biases"],"prefix":"10.1109","author":[{"given":"Yuya Jeremy","family":"Ong","sequence":"first","affiliation":[{"name":"IBM Research - Almaden,San Jose,California"}]},{"given":"Jay","family":"Gala","sequence":"additional","affiliation":[{"name":"IBM Research - Almaden,San Jose,California"}]},{"given":"Sungeun","family":"An","sequence":"additional","affiliation":[{"name":"IBM Research - Almaden,San Jose,California"}]},{"given":"Robert","family":"Moore","sequence":"additional","affiliation":[{"name":"IBM Research - Almaden,San Jose,California"}]},{"given":"Divyesh","family":"Jadav","sequence":"additional","affiliation":[{"name":"IBM Research - Almaden,San Jose,California"}]}],"member":"263","reference":[{"year":"2024","key":"ref1","article-title":"Chatgpt"},{"year":"2024","key":"ref2","article-title":"Google gemini"},{"year":"2024","key":"ref3","article-title":"Claude"},{"journal-title":"IBM Research, Tech. Rep.","article-title":"Granite Foundation Models","year":"2023","key":"ref4"},{"article-title":"Google apologizes for \"missing the mark\" after gemini generated racially diverse nazis","year":"2024","author":"Robertson","key":"ref5"},{"article-title":"Gradient-based language model red teaming","year":"2024","author":"Wichers","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0146167217741313"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i19.30142"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.176"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.485"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.165"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.42"},{"journal-title":"Fairness in serving large language models","year":"2023","author":"Sheng","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.812"},{"journal-title":"Auditing and mitigating cultural bias in llms","year":"2023","author":"Tao","key":"ref15"},{"journal-title":"Bias runs deep: Implicit reasoning biases in persona-assigned llms","year":"2023","author":"Gupta","key":"ref16"},{"journal-title":"Subtle misogyny detection and mitigation: An expert-annotated dataset","year":"2023","author":"Sheppard","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.625"},{"journal-title":"The tail wagging the dog: Dataset construction biases of social bias benchmarks","year":"2022","author":"Selvam","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445924"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.154"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.416"},{"journal-title":"Measure and improve robustness in nlp models: A survey","year":"2021","author":"Wang","key":"ref23"},{"journal-title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models","year":"2022","author":"Srivastava","key":"ref24"},{"journal-title":"Holistic evaluation of language models","year":"2022","author":"Liang","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.311"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594109"},{"journal-title":"Queens are powerful too: Mitigating gender bias in dialogue generation","year":"2019","author":"Dinan","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.151"},{"key":"ref30","first-page":"2611","article-title":"Bias out-of-the-box: An empirical analysis of intersectional occupational biases in popular generative language models","volume":"34","author":"Kirk","year":"2021","journal-title":"Advances in neural information processing systems"},{"journal-title":"Building guardrails for large language models","year":"2024","author":"Dong","key":"ref31"},{"journal-title":"Ul2: Unifying language learning paradigms","year":"2022","author":"Tay","key":"ref32"},{"journal-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref33"},{"journal-title":"The llama 3 herd of models","year":"2024","author":"Dubey","key":"ref34"},{"journal-title":"Mixtral of experts","year":"2024","author":"Jiang","key":"ref35"},{"journal-title":"Qwen2 technical report","year":"2024","author":"Yang","key":"ref36"},{"journal-title":"Lab: Large-scale alignment for chatbots","year":"2024","author":"Sudalairaj","key":"ref37"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","start":{"date-parts":[[2024,12,15]]},"location":"Washington, DC, USA","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\/10825408.pdf?arnumber=10825408","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:46:40Z","timestamp":1737100000000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10825408\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10825408","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}