White Men Lead, Black Women Help: Uncovering Gender, Racial, and Intersectional Bias in Language Agency

Social biases can manifest in language agency. For instance, White individuals and men are often described as "agentic" and achievement-oriented, whereas Black individuals and women are frequently described as "communal" and as assisting roles. This study establishes agency as an important aspect of studying social biases in both human-written and Large Language Model (LLM)-generated texts. To accurately measure "language agency" at sentence level, we propose a Language Agency Classification dataset to train reliable agency classifiers. We then use an agency classifier to reveal notable language agency biases in 6 datasets of human- or LLM-written texts, including biographies, professor reviews, and reference letters. While most prior NLP research on agency biases focused on single dimensions, we comprehensively explore language agency biases in gender, race, and intersectional identities. We observe that (1) language agency biases in human-written texts align with real-world social observations; (2) LLM-generated texts demonstrate remarkably higher levels of language agency bias than human-written texts; and (3) critical biases in language agency target people of minority groups -- for instance, languages used to describe Black females exhibit the lowest level of agency across datasets. Our findings reveal intricate social biases in human- and LLM-written texts through the lens of language agency, warning against using LLM generations in social contexts without scrutiny.

Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation

The recent advancement of large and powerful models with Text-to-Image (T2I) generation abilities -- such as OpenAI's DALLE-3 and Google's Gemini -- enables users to generate high-quality images from textual prompts. However, it has become increasingly evident that even simple prompts could cause T2I models to exhibit conspicuous social bias in generated images. Such bias might lead to both allocational and representational harms in society, further marginalizing minority groups. Noting this problem, a large body of recent works has been dedicated to investigating different dimensions of bias in T2I systems. However, an extensive review of these studies is lacking, hindering a systematic understanding of current progress and research gaps. We present the first extensive survey on bias in T2I generative models. In this survey, we review prior studies on dimensions of bias: Gender, Skintone, and Geo-Culture. Specifically, we discuss how these works define, evaluate, and mitigate different aspects of bias. We found that: (1) while gender and skintone biases are widely studied, geo-cultural bias remains under-explored; (2) most works on gender and skintone bias investigated occupational association, while other aspects are less frequently studied; (3) almost all gender bias works overlook non-binary identities in their studies; (4) evaluation datasets and metrics are scattered, with no unified framework for measuring biases; and (5) current mitigation methods fail to resolve biases comprehensively. Based on current limitations, we point out future research directions that contribute to human-centric definitions, evaluations, and mitigation of biases. We hope to highlight the importance of studying biases in T2I systems, as well as encourage future efforts to holistically understand and tackle biases, building fair and trustworthy T2I technologies for everyone.

The Male CEO and the Female Assistant: Probing Gender Biases in Text-To-Image Models Through Paired Stereotype Test

Recent large-scale Text-To-Image (T2I) models such as DALLE-3 demonstrate great potential in new applications, but also face unprecedented fairness challenges. Prior studies revealed gender biases in single-person image generation, but T2I model applications might require portraying two or more people simultaneously. Potential biases in this setting remain unexplored, leading to fairness-related risks in usage. To study these underlying facets of gender biases in T2I models, we propose a novel Paired Stereotype Test (PST) bias evaluation framework. PST prompts the model to generate two individuals in the same image. They are described with two social identities that are stereotypically associated with the opposite gender. Biases can then be measured by the level of conformation to gender stereotypes in generated images. Using PST, we evaluate DALLE-3 from 2 perspectives: biases in gendered occupation and biases in organizational power. Despite seemingly fair or even anti-stereotype single-person generations, PST still unveils gendered occupational and power associations. Moreover, compared to single-person settings, DALLE-3 generates noticeably more masculine figures under PST for individuals with male-stereotypical identities. PST is therefore effective in revealing underlying gender biases in DALLE-3 that single-person settings cannot capture. Our findings reveal the complicated patterns of gender biases in modern T2I models, further highlighting the critical fairness challenges in multimodal generative systems.

Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generation

Model hallucination has been a crucial interest of research in Natural Language Generation (NLG). In this work, we propose sequence-level certainty as a common theme over hallucination in NLG, and explore the correlation between sequence-level certainty and the level of hallucination in model responses. We categorize sequence-level certainty into two aspects: probabilistic certainty and semantic certainty, and reveal through experiments on Knowledge-Grounded Dialogue Generation (KGDG) task that both a higher level of probabilistic certainty and a higher level of semantic certainty in model responses are significantly correlated with a lower level of hallucination. What's more, we provide theoretical proof and analysis to show that semantic certainty is a good estimator of probabilistic certainty, and therefore has the potential as an alternative to probability-based certainty estimation in black-box scenarios. Based on the observation on the relationship between certainty and hallucination, we further propose Certainty-based Response Ranking (CRR), a decoding-time method for mitigating hallucination in NLG. Based on our categorization of sequence-level certainty, we propose 2 types of CRR approach: Probabilistic CRR (P-CRR) and Semantic CRR (S-CRR). P-CRR ranks individually sampled model responses using their arithmetic mean log-probability of the entire sequence. S-CRR approaches certainty estimation from meaning-space, and ranks a number of model response candidates based on their semantic certainty level, which is estimated by the entailment-based Agreement Score (AS). Through extensive experiments across 3 KGDG datasets, 3 decoding methods, and on 4 different models, we validate the effectiveness of our 2 proposed CRR methods to reduce model hallucination.

"Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters

Large Language Models (LLMs) have recently emerged as an effective tool to assist individuals in writing various types of content, including professional documents such as recommendation letters. Though bringing convenience, this application also introduces unprecedented fairness concerns. Model-generated reference letters might be directly used by users in professional scenarios. If underlying biases exist in these model-constructed letters, using them without scrutinization could lead to direct societal harms, such as sabotaging application success rates for female applicants. In light of this pressing issue, it is imminent and necessary to comprehensively study fairness issues and associated harms in this real-world use case. In this paper, we critically examine gender biases in LLM-generated reference letters. Drawing inspiration from social science findings, we design evaluation methods to manifest biases through 2 dimensions: (1) biases in language style and (2) biases in lexical content. We further investigate the extent of bias propagation by analyzing the hallucination bias of models, a term that we define to be bias exacerbation in model-hallucinated contents. Through benchmarking evaluation on 2 popular LLMs- ChatGPT and Alpaca, we reveal significant gender biases in LLM-generated recommendation letters. Our findings not only warn against using LLMs for this application without scrutinization, but also illuminate the importance of thoroughly studying hidden biases and harms in LLM-generated professional documents.

Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems

Recent advancements in Large Language Models empower them to follow freeform instructions, including imitating generic or specific demographic personas in conversations. We define generic personas to represent demographic groups, such as "an Asian person", whereas specific personas may take the form of specific popular Asian names like "Yumi". While the adoption of personas enriches user experiences by making dialogue systems more engaging and approachable, it also casts a shadow of potential risk by exacerbating social biases within model responses, thereby causing societal harm through interactions with users. In this paper, we systematically study "persona biases", which we define to be the sensitivity of dialogue models' harmful behaviors contingent upon the personas they adopt. We categorize persona biases into biases in harmful expression and harmful agreement, and establish a comprehensive evaluation framework to measure persona biases in five aspects: Offensiveness, Toxic Continuation, Regard, Stereotype Agreement, and Toxic Agreement. Additionally, we propose to investigate persona biases by experimenting with UNIVERSALPERSONA, a systematically constructed persona dataset encompassing various types of both generic and specific model personas. Through benchmarking on four different models -- including Blender, ChatGPT, Alpaca, and Vicuna -- our study uncovers significant persona biases in dialogue systems. Our findings also underscore the pressing need to revisit the use of personas in dialogue agents to ensure safe application.

PIP: Parse-Instructed Prefix for Syntactically Controlled Paraphrase Generation

Syntactically controlled paraphrase generation requires language models to generate paraphrases for sentences according to specific syntactic structures. Existing fine-tuning methods for this task are costly as all the parameters of the model need to be updated during the training process. Inspired by recent studies on parameter-efficient learning, we propose Parse-Instructed Prefix (PIP), a novel adaptation of prefix-tuning to tune large pre-trained language models on syntactically controlled paraphrase generation task in a low-data setting with significantly less training cost. We introduce two methods to instruct a model's encoder prefix to capture syntax-related knowledge: direct initiation (PIP-Direct) and indirect optimization (PIP-Indirect). In contrast to traditional fine-tuning methods for this task, PIP is a compute-efficient alternative with 10 times less learnable parameters. Compared to existing prefix-tuning methods, PIP excels at capturing syntax control information, achieving significantly higher performance at the same level of learnable parameter count.