With the advance of Artificial Intelligence (AI), Large Language Models (LLMs) have gained prominence and been applied in diverse contexts. As they evolve into more sophisticated versions, it is essential to assess whether they reproduce biases, such as discrimination and racialization, while maintaining hegemonic discourses. Current bias detection approaches rely mostly on quantitative, automated methods, which often overlook the nuanced ways in which biases emerge in natural language. This study proposes a qualitative, discursive framework to complement such methods. Through manual analysis of LLM-generated short stories featuring Black and white women, we investigate gender and racial biases. We contend that qualitative methods such as the one proposed here are fundamental to help both developers and users identify the precise ways in which biases manifest in LLM outputs, thus enabling better conditions to mitigate them. Results show that Black women are portrayed as tied to ancestry and resistance, while white women appear in self-discovery processes. These patterns reflect how language models replicate crystalized discursive representations, reinforcing essentialization and a sense of social immobility. When prompted to correct biases, models offered superficial revisions that maintained problematic meanings, revealing limitations in fostering inclusive narratives. Our results demonstrate the ideological functioning of algorithms and have significant implications for the ethical use and development of AI. The study reinforces the need for critical, interdisciplinary approaches to AI design and deployment, addressing how LLM-generated discourses reflect and perpetuate inequalities.

Multimodal large language models (MLLMs) have shown impressive capabilities across tasks involving both visual and textual modalities. However, growing concerns remain about their potential to encode and amplify gender bias, particularly in socially sensitive applications. Existing benchmarks predominantly evaluate bias in isolated scenarios, overlooking how bias may emerge subtly through interpersonal interactions. We fill this gap by going beyond single-entity evaluation and instead focusing on a deeper examination of relational and contextual gender bias in dual-individual interactions. We introduce Genres, a novel benchmark designed to evaluate gender bias in MLLMs through the lens of social relationships in generated narratives. Genres assesses gender bias through a dual-character profile and narrative generation task that captures rich interpersonal dynamics and supports a fine-grained bias evaluation suite across multiple dimensions. Experiments on both open- and closed-source MLLMs reveal persistent, context-sensitive gender biases that are not evident in single-character settings. Our findings underscore the importance of relationship-aware benchmarks for diagnosing subtle, interaction-driven gender bias in MLLMs and provide actionable insights for future bias mitigation.

Large Language Models (LLMs) have revolutionized natural language processing, yet concerns persist regarding their tendency to reflect or amplify social biases present in their training data. This study introduces a novel evaluation framework to uncover gender biases in LLMs, focusing on their occupational narratives. Unlike previous methods relying on structured scenarios or carefully crafted prompts, our approach leverages free-form storytelling to reveal biases embedded in the models. Systematic analyses show an overrepresentation of female characters across occupations in six widely used LLMs. Additionally, our findings reveal that LLM-generated occupational gender rankings align more closely with human stereotypes than actual labor statistics. These insights underscore the need for balanced mitigation strategies to ensure fairness while avoiding the reinforcement of new stereotypes.

In Spain, the Baroque period, was a period of immense artistic creativity, genereally known as the "Golden Age" (siglo de oro). This is particularly true in literature, where the period saw exceptional writers such as Lope de Vega, Tirso de Molina or Pedro Calderón de la Barca. The latter, who lived from 1600 to 1681, is generally considered as as one of the most important playwrights of the age. He was immensely productive, writing a total of over 200 theatrical plays, both secular and religious, which had a lasting impact on Spanish theatre and beyond [17]. He is particularly known for detailed and complex characterizations in his works [46]. Not surprisingly, Calderón's writings have been subject to intense analysis by literary scholars over a long period of time, and topics have moved in and out of fashion. For example, traditional foci of scholarship have been the role of honor and power in the works [19] or Calderón's attention to dramatic structure [43]. A relatively new aspect among these is gender depiction, that is, the question of how Calderón conceptualized male and female roles in his plays differently, which has gained global attention in Hispanic Studies since the latter half of the 20th century ([2, 32, 39]).

Large Language Models (LLMs) have shown remarkable capabilities in a multitude of Natural Language Processing (NLP) tasks. However, these models are still not immune to limitations such as social biases, especially gender bias. This work investigates whether current closed and open-source LLMs possess gender bias, especially when asked to give moral opinions. To evaluate these models, we curate and introduce a new dataset GenMO (Gender-bias in Morality Opinions) comprising parallel short stories featuring male and female characters respectively. Specifically, we test models from the GPT family (GPT-3.5-turbo, GPT-3.5-turbo-instruct, GPT-4-turbo), Llama 3 and 3.1 families (8B/70B), Mistral-7B and Claude 3 families (Sonnet and Opus). Surprisingly, despite employing safety checks, all production-standard models we tested display significant gender bias with GPT-3.5-turbo giving biased opinions in 24% of the samples. Additionally, all models consistently favour female characters, with GPT showing bias in 68-85% of cases and Llama 3 in around 81-85% instances. Additionally, our study investigates the impact of model parameters on gender bias and explores real-world situations where LLMs reveal biases in moral decision-making.

A few months ago I wrote about a consulting agency, Sweet Baby Inc, that found itself at the centre of a conspiracy theory: aggrieved gamers on a Steam forum had erroneously concluded that this small agency was somehow mandating the inclusion of more diverse characters in games. Depressingly but unsurprisingly, the result was a tremendous amount of targeted harassment towards the people who work at Sweet Baby and every journalist who reported on it (particularly the women). It was a disturbing echo of Gamergate, an online harassment campaign 10 years ago that initially sprung from the wild accusations of a game developer's vindictive ex-boyfriend. The language has changed a bit in the past decade: they used to be upset about "SJWs", or social justice warriors, and now they've taken issue with a different acronym, DEI (diversity, equality and inclusion), or just good ol' "woke". But the sentiment from this group is the same: games are for us, and for us only, and if you want games to change, or to tell stories outside the straightforward male-oriented power fantasies that we grew up with, then, well, that's not allowed.

I'm a guy "in real life," but I've always played female characters in video games. More and more people say this means I'm either secretly gay/trans or a total creep. Am I allowed to just prefer it? For timely guidance on encounters with technology, open a support ticket via email; or register and post a comment below. It sounds like you have a lot of people in your life, Player, who think they know you better than you know yourself.

Inspired by the concept of the male gaze (Mulvey, 1975) in literature and media studies, this paper proposes a framework for analyzing gender bias in terms of female objectification: the extent to which a text portrays female individuals as objects of visual pleasure. Our framework measures female objectification along two axes. First, we compute an agency bias score that indicates whether male entities are more likely to appear in the text as grammatical agents than female entities. Next, by analyzing the word embedding space induced by a text (Caliskan et al., 2017), we compute an appearance bias score that indicates whether female entities are more closely associated with appearance-related words than male entities. Applying our framework to 19th and 20th century novels reveals evidence of female objectification in literature: we find that novels written from a male perspective systematically objectify female characters, while novels written from a female perspective do not exhibit statistically significant objectification of any gender.

When I listen to the voice recording I made at the Irvine, California, headquarters of the video-game company Blizzard Entertainment this past January, I hear a noise that many gamers find blissful: the sound of utter mayhem. Playing a prerelease version of Diablo IV, the latest installment in a 26-year-old adventure series about battling the forces of hell, I faced swarms of demons that yowled and belched. I jabbed buttons arrhythmically--click … click … clickclickclick--while trying to stifle curses and whimpers. But the strangest sounds came from the two Diablo IV designers who sat alongside me. As I dueled with an angry sea witch, Joseph Piepiora, an associate game director, gently noted that I was low on healing potions.

Social biases and stereotypes are embedded in our culture in part through their presence in our stories, as evidenced by the rich history of humanities and social science literature analyzing such biases in children stories. Because these analyses are often conducted manually and at a small scale, such investigations can benefit from the use of more recent natural language processing methods that examine social bias in models and data corpora. Our work joins this interdisciplinary effort and makes a unique contribution by taking into account the event narrative structures when analyzing the social bias of stories. We propose a computational pipeline that automatically extracts a story's temporal narrative verb-based event chain for each of its characters as well as character attributes such as gender. We also present a verb-based event annotation scheme that can facilitate bias analysis by including categories such as those that align with traditional stereotypes. Through a case study analyzing gender bias in fairy tales, we demonstrate that our framework can reveal bias in not only the unigram verb-based events in which female and male characters participate but also in the temporal narrative order of such event participation.