{"arxiv_id":"2608.14692","incoming":{"papers":0,"sentences":0,"groups":[],"unlabelled_sentences":0},"outgoing":{"papers":23,"sentences":44,"groups":[{"kind":"extends","label":"Builds on","papers":2,"sentences":2,"quotes":[{"arxiv_id":"2402.05070","title":"A Roadmap to Pluralistic Alignment","url":"/paper/2402.05070","section":"Auditing Approaches Presuppose Non-Pluralistic Definitions of Harm","sentence":"Prior work has highlighted the challenges of pluralistic alignment, where generative AI systems overlook human social diversity between groups [ref] ; we extend this idea to within-group diversity and highlight the pitfalls of documenting harms and preferences at the group level.","intent_p":0.99,"contests_p":null},{"arxiv_id":"2511.14476","title":null,"url":"/paper/2511.14476","section":"Auditing Approaches Presuppose Non-Pluralistic Definitions of Harm","sentence":"Prior work has highlighted the challenges of pluralistic alignment, where generative AI systems overlook human social diversity between groups [ref] ; we extend this idea to within-group diversity and highlight the pitfalls of documenting harms and preferences at the group level.","intent_p":0.99,"contests_p":null}]},{"kind":"supports_this_paper","label":"Cites as support","papers":7,"sentences":9,"quotes":[{"arxiv_id":"2503.19075","title":null,"url":"/paper/2503.19075","section":"Surfacing Harms Via Algorithm Auditing","sentence":"Users can discover nuanced and community-specific harms that have previously been overlooked by researchers or practitioners [ref] .","intent_p":1.0,"contests_p":null},{"arxiv_id":"2503.17482","title":null,"url":"/paper/2503.17482","section":"Asymmetry of Labor","sentence":"Additionally, even if users were to articulate harms as they occur, the lack of transparency in current AI systems [ref] and the difficulty for users to steer AI system behavior [ref] make it unclear whether this labor would prevent harms in future outputs.","intent_p":0.99,"contests_p":null},{"arxiv_id":"2409.03307","title":"AI data transparency: an exploration through the lens of AI incidents","url":"/paper/2409.03307","section":"Asymmetry of Labor","sentence":"Additionally, even if users were to articulate harms as they occur, the lack of transparency in current AI systems [ref] and the difficulty for users to steer AI system behavior [ref] make it unclear whether this labor would prevent harms in future outputs.","intent_p":0.99,"contests_p":null},{"arxiv_id":"2402.14875","title":"What's in a Name? Auditing Large Language Models for Race and Gender Bias","url":"/paper/2402.14875","section":"Auditing Approaches Presuppose Harm as Static","sentence":"Empirical audits of large language models typically rely on one-off evaluations, such as static benchmark datasets [ref] , prompt sets [ref] , or simulated personas [ref] , to assess harmful behaviors.","intent_p":0.97,"contests_p":null},{"arxiv_id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","url":"/paper/2005.14050","section":"Auditing Approaches Presuppose Harm as Static","sentence":"Empirical audits of large language models typically rely on one-off evaluations, such as static benchmark datasets [ref] , prompt sets [ref] , or simulated personas [ref] , to assess harmful behaviors.","intent_p":0.97,"contests_p":null}]},{"kind":"background","label":"Cites as background","papers":3,"sentences":3,"quotes":[{"arxiv_id":"2511.01805","title":null,"url":"/paper/2511.01805","section":"Personalized, Generative AI Systems","sentence":"Recent work has attempted to better understand and evaluate how personalized interaction can affect behaviors for generative AI systems, such as chatbots [ref] .","intent_p":0.82,"contests_p":null},{"arxiv_id":"2401.14462","title":"AI auditing: The Broken Bus on the Road to AI Accountability","url":"/paper/2401.14462","section":"Surfacing Harms Via Algorithm Auditing","sentence":"Algorithm auditing describes the process of surfacing harms by directly analyzing the outputs of such systems [ref] .","intent_p":0.86,"contests_p":null},{"arxiv_id":"2406.16937","title":"A Complete Survey on LLM-based AI Chatbots","url":"/paper/2406.16937","section":"Introduction","sentence":"Generative AI systems are being increasingly integrated into everyday applications, such as chatbots [ref] and writing assistants [ref] .","intent_p":0.96,"contests_p":null}]}],"unlabelled_sentences":30},"claims":[],"thresholds":{"intent_p":0.8,"supports_p":0.95,"contests_p":0.7},"method":"Citing sentences come from each paper's LaTeX source; every \\cite marks the sentence and the works it cites. Pith's classifier typed each sentence. A label is shown at intent probability 0.8 or more (0.95 for support), a contest at 0.7 or more. Measured accuracy against two blind model families is at https://pith.science/accuracy. The quoted sentences are the citing authors' own.","held_up":null,"_links":{"html":"https://pith.science/paper/2608.14692"}}