回溯與追溯：與生成式語言模型對話

Recourse for reclamation: Chatting with generative language models

March 21, 2024

作者: Jennifer Chien, Kevin R. McKee, Jackie Kay, William Isaac

cs.AI

摘要

研究人員和開發者越來越依賴毒性評分來調節生成式語言模型的輸出，在客戶服務、信息檢索和內容生成等場景中。然而，毒性評分可能導致相關信息無法獲取，使文化規範僵化或「價值鎖定」，並阻礙語言重擁有過程，特別是對於邊緣化群體。在這項工作中，我們將算法回溯的概念擴展到生成式語言模型：我們為用戶提供一種新機制，通過動態設置毒性過濾的閾值來實現他們期望的預測。用戶因此相對於與基準系統互動，行使了更多的代理權。一項初步研究（n = 30）支持我們提出的回溯機制的潛力，顯示與模型輸出的固定閾值毒性過濾相比，在可用性方面有所改善。未來的工作應該探索毒性評分、模型可控性、用戶代理權和語言重擁有過程的交集，特別是關於許多社區在與生成式語言模型互動時遇到的偏見。

English

Researchers and developers increasingly rely on toxicity scoring to moderate generative language model outputs, in settings such as customer service, information retrieval, and content generation. However, toxicity scoring may render pertinent information inaccessible, rigidify or "value-lock" cultural norms, and prevent language reclamation processes, particularly for marginalized people. In this work, we extend the concept of algorithmic recourse to generative language models: we provide users a novel mechanism to achieve their desired prediction by dynamically setting thresholds for toxicity filtering. Users thereby exercise increased agency relative to interactions with the baseline system. A pilot study (n = 30) supports the potential of our proposed recourse mechanism, indicating improvements in usability compared to fixed-threshold toxicity-filtering of model outputs. Future work should explore the intersection of toxicity scoring, model controllability, user agency, and language reclamation processes -- particularly with regard to the bias that many communities encounter when interacting with generative language models.