arXiv subjects

Svetlana Kiritchenko

Publications and source records attributed to Svetlana Kiritchenko.

At least 19 recordsLinked to original sources

arXiv2026

Safety Measurements for Fine-tuned LLMs Should be Grounded in Capability

Adapting foundation large language models to a user's task or preferred style through fine-tuning can result in compromising the model's safety. Previous works examined the effects of fine-tuning on model safety in limited and seemingly random experimental settings. We argue that anchoring fine-tuning to a specific capability goal is essential for avoiding arbitrary empirical choices, allowing us to draw meaningful conclusions about safety impacts, and to compare mitigation methods on a consistent basis. We conduct a multi-dimensional evaluation of the effects of fine-tuning on model behavior by focusing on capability as well as safety. Our results surface important issues that (1) fine-tuned models can produce incoherent generations in response to safety prompts, (2) automated safety judgments are unreliable for such incoherent outputs, and (3) the conclusions about the effects of fine-tuning can change depending on the choice of safety benchmark as well as the safety evaluator.

cs.CL↗

arXiv2025

From Perceived Effectiveness to Measured Impact: Identity-Aware Evaluation of Automated Counter-Stereotypes

We investigate the effect of automatically generated counter-stereotypes on gender bias held by users of various demographics on social media. Building on recent NLP advancements and social psychology literature, we evaluate two counter-stereotype strategies -- counter-facts and broadening universals (i.e., stating that anyone can have a trait regardless of group membership) -- which have been identified as the most potentially effective in previous studies. We assess the real-world impact of these strategies on mitigating gender bias across user demographics (gender and age), through the Implicit Association Test and the self-reported measures of explicit bias and perceived utility. Our findings reveal that actual effectiveness does not align with perceived effectiveness, and the former is a nuanced and sometimes divergent phenomenon across demographic groups. While overall bias reduction was limited, certain groups (e.g., older, male participants) exhibited measurable improvements in implicit bias in response to some interventions. Conversely, younger participants, especially women, showed increasing bias in response to the same interventions. These results highlight the complex and identity-sensitive nature of stereotype mitigation and call for dynamic and context-aware evaluation and mitigation strategies.

cs.CY↗

arXiv2025

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency

Fine-tuning a general-purpose large language model (LLM) for a specific domain or task has become a routine procedure for ordinary users. However, fine-tuning is known to remove the safety alignment features of the model, even when the fine-tuning data does not contain any harmful content. We consider this to be a critical failure mode of LLMs due to the widespread uptake of fine-tuning, combined with the benign nature of the "attack". Most well-intentioned developers are likely unaware that they are deploying an LLM with reduced safety. On the other hand, this known vulnerability can be easily exploited by malicious actors intending to bypass safety guardrails. To make any meaningful progress in mitigating this issue, we first need reliable and reproducible safety evaluations. In this work, we investigate how robust a safety benchmark is to trivial variations in the experimental procedure, and the stochastic nature of LLMs. Our initial experiments expose surprising variance in the results of the safety evaluation, even when seemingly inconsequential changes are made to the fine-tuning setup. Our observations have serious implications for how researchers in this field should report results to enable meaningful comparisons in the future.

cs.CL↗

arXiv2025

When Detection Fails: The Power of Fine-Tuned Models to Generate Human-Like Social Media Text

Detecting AI-generated text is a difficult problem to begin with; detecting AI-generated text on social media is made even more difficult due to the short text length and informal, idiosyncratic language of the internet. It is nonetheless important to tackle this problem, as social media represents a significant attack vector in online influence campaigns, which may be bolstered through the use of mass-produced AI-generated posts supporting (or opposing) particular policies, decisions, or events. We approach this problem with the mindset and resources of a reasonably sophisticated threat actor, and create a dataset of 505,159 AI-generated social media posts from a combination of open-source, closed-source, and fine-tuned LLMs, covering 11 different controversial topics. We show that while the posts can be detected under typical research assumptions about knowledge of and access to the generating models, under the more realistic assumption that an attacker will not release their fine-tuned model to the public, detectability drops dramatically. This result is confirmed with a human study. Ablation experiments highlight the vulnerability of various detection algorithms to fine-tuned LLMs. This result has implications across all detection domains, since fine-tuning is a generally applicable and realistic LLM use case.

cs.CL↗

arXiv2025

Uncovering Bias in Large Vision-Language Models at Scale with Counterfactuals

With the advent of Large Language Models (LLMs) possessing increasingly impressive capabilities, a number of Large Vision-Language Models (LVLMs) have been proposed to augment LLMs with visual inputs. Such models condition generated text on both an input image and a text prompt, enabling a variety of use cases such as visual question answering and multimodal chat. While prior studies have examined the social biases contained in text generated by LLMs, this topic has been relatively unexplored in LVLMs. Examining social biases in LVLMs is particularly challenging due to the confounding contributions of bias induced by information contained across the text and visual modalities. To address this challenging problem, we conduct a large-scale study of text generated by different LVLMs under counterfactual changes to input images, producing over 57 million responses from popular models. Our multi-dimensional bias evaluation framework reveals that social attributes such as perceived race, gender, and physical characteristics depicted in images can significantly influence the generation of toxic content, competency-associated words, harmful stereotypes, and numerical ratings of individuals.

cs.CV↗

arXiv2025

Tackling Social Bias against the Poor: A Dataset and Taxonomy on Aporophobia

Eradicating poverty is the first goal in the United Nations Sustainable Development Goals. However, aporophobia -- the societal bias against people living in poverty -- constitutes a major obstacle to designing, approving and implementing poverty-mitigation policies. This work presents an initial step towards operationalizing the concept of aporophobia to identify and track harmful beliefs and discriminative actions against poor people on social media. In close collaboration with non-profits and governmental organizations, we conduct data collection and exploration. Then we manually annotate a corpus of English tweets from five world regions for the presence of (1) direct expressions of aporophobia, and (2) statements referring to or criticizing aporophobic views or actions of others, to comprehensively characterize the social media discourse related to bias and discrimination against the poor. Based on the annotated data, we devise a taxonomy of categories of aporophobic attitudes and actions expressed through speech on social media. Finally, we train several classifiers and identify the main challenges for automatic detection of aporophobia in social networks. This work paves the way towards identifying, tracking, and mitigating aporophobic views on social media at scale.

cs.CY↗

arXiv2025

Detecting AI-Generated Text: Factors Influencing Detectability with Current Methods

Large language models (LLMs) have advanced to a point that even humans have difficulty discerning whether a text was generated by another human, or by a computer. However, knowing whether a text was produced by human or artificial intelligence (AI) is important to determining its trustworthiness, and has applications in many domains including detecting fraud and academic dishonesty, as well as combating the spread of misinformation and political propaganda. The task of AI-generated text (AIGT) detection is therefore both very challenging, and highly critical. In this survey, we summarize state-of-the art approaches to AIGT detection, including watermarking, statistical and stylistic analysis, and machine learning classification. We also provide information about existing datasets for this task. Synthesizing the research findings, we aim to provide insight into the salient factors that combine to determine how "detectable" AIGT text is under different scenarios, and to make practical recommendations for future work towards this significant technical and societal challenge.

cs.CL↗

arXiv2024

Adaptable Moral Stances of Large Language Models on Sexist Content: Implications for Society and Gender Discourse

This work provides an explanatory view of how LLMs can apply moral reasoning to both criticize and defend sexist language. We assessed eight large language models, all of which demonstrated the capability to provide explanations grounded in varying moral perspectives for both critiquing and endorsing views that reflect sexist assumptions. With both human and automatic evaluation, we show that all eight models produce comprehensible and contextually relevant text, which is helpful in understanding diverse views on how sexism is perceived. Also, through analysis of moral foundations cited by LLMs in their arguments, we uncover the diverse ideological perspectives in models' outputs, with some models aligning more with progressive or conservative views on gender roles and sexism. Based on our observations, we caution against the potential misuse of LLMs to justify sexist language. We also highlight that LLMs can serve as tools for understanding the roots of sexist beliefs and designing well-informed interventions. Given this dual capacity, it is crucial to monitor LLMs and design safety mechanisms for their use in applications that involve sensitive societal topics, such as sexism.

cs.CL↗

arXiv2024

Uncovering Bias in Large Vision-Language Models with Counterfactuals

With the advent of Large Language Models (LLMs) possessing increasingly impressive capabilities, a number of Large Vision-Language Models (LVLMs) have been proposed to augment LLMs with visual inputs. Such models condition generated text on both an input image and a text prompt, enabling a variety of use cases such as visual question answering and multimodal chat. While prior studies have examined the social biases contained in text generated by LLMs, this topic has been relatively unexplored in LVLMs. Examining social biases in LVLMs is particularly challenging due to the confounding contributions of bias induced by information contained across the text and visual modalities. To address this challenging problem, we conduct a large-scale study of text generated by different LVLMs under counterfactual changes to input images. Specifically, we present LVLMs with identical open-ended text prompts while conditioning on images from different counterfactual sets, where each set contains images which are largely identical in their depiction of a common subject (e.g., a doctor), but vary only in terms of intersectional social attributes (e.g., race and gender). We comprehensively evaluate the text produced by different LVLMs under this counterfactual generation setting and find that social attributes such as race, gender, and physical characteristics depicted in input images can significantly influence toxicity and the generation of competency-associated words.

cs.CV↗

arXiv2024

Challenging Negative Gender Stereotypes: A Study on the Effectiveness of Automated Counter-Stereotypes

Gender stereotypes are pervasive beliefs about individuals based on their gender that play a significant role in shaping societal attitudes, behaviours, and even opportunities. Recognizing the negative implications of gender stereotypes, particularly in online communications, this study investigates eleven strategies to automatically counter-act and challenge these views. We present AI-generated gender-based counter-stereotypes to (self-identified) male and female study participants and ask them to assess their offensiveness, plausibility, and potential effectiveness. The strategies of counter-facts and broadening universals (i.e., stating that anyone can have a trait regardless of group membership) emerged as the most robust approaches, while humour, perspective-taking, counter-examples, and empathy for the speaker were perceived as less effective. Also, the differences in ratings were more pronounced for stereotypes about the different targets than between the genders of the raters. Alarmingly, many AI-generated counter-stereotypes were perceived as offensive and/or implausible. Our analysis and the collected dataset offer foundational insight into counter-stereotype generation, guiding future efforts to develop strategies that effectively challenge gender stereotypes in online interactions.

cs.CL↗

arXiv2024

Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Images

Following on recent advances in large language models (LLMs) and subsequent chat models, a new wave of large vision-language models (LVLMs) has emerged. Such models can incorporate images as input in addition to text, and perform tasks such as visual question answering, image captioning, story generation, etc. Here, we examine potential gender and racial biases in such systems, based on the perceived characteristics of the people in the input images. To accomplish this, we present a new dataset PAIRS (PArallel Images for eveRyday Scenarios). The PAIRS dataset contains sets of AI-generated images of people, such that the images are highly similar in terms of background and visual content, but differ along the dimensions of gender (man, woman) and race (Black, white). By querying the LVLMs with such images, we observe significant differences in the responses according to the perceived gender or race of the person depicted.

cs.CY↗

arXiv2023

Concept-Based Explanations to Test for False Causal Relationships Learned by Abusive Language Classifiers

Classifiers tend to learn a false causal relationship between an over-represented concept and a label, which can result in over-reliance on the concept and compromised classification accuracy. It is imperative to have methods in place that can compare different models and identify over-reliances on specific concepts. We consider three well-known abusive language classifiers trained on large English datasets and focus on the concept of negative emotions, which is an important signal but should not be learned as a sufficient feature for the label of abuse. Motivated by the definition of global sufficiency, we first examine the unwanted dependencies learned by the classifiers by assessing their accuracy on a challenge set across all decision thresholds. Further, recognizing that a challenge set might not always be available, we introduce concept-based explanation metrics to assess the influence of the concept on the labels. These explanations allow us to compare classifiers regarding the degree of false global sufficiency they have learned between a concept and a label.

cs.CL↗

arXiv2023

The crime of being poor

The criminalization of poverty has been widely denounced as a collective bias against the most vulnerable. NGOs and international organizations claim that the poor are blamed for their situation, are more often associated with criminal offenses than the wealthy strata of society and even incur criminal offenses simply as a result of being poor. While no evidence has been found in the literature that correlates poverty and overall criminality rates, this paper offers evidence of a collective belief that associates both concepts. This brief report measures the societal bias that correlates criminality with the poor, as compared to the rich, by using Natural Language Processing (NLP) techniques in Twitter. The paper quantifies the level of crime-poverty bias in a panel of eight different English-speaking countries. The regional differences in the association between crime and poverty cannot be justified based on different levels of inequality or unemployment, which the literature correlates to property crimes. The variation in the observed rates of crime-poverty bias for different geographic locations could be influenced by cultural factors and the tendency to overestimate the equality of opportunities and social mobility in specific countries. These results have consequences for policy-making and open a new path of research for poverty mitigation with the focus not only on the poor but on society as a whole. Acting on the collective bias against the poor would facilitate the approval of poverty reduction policies, as well as the restoration of the dignity of the persons affected.

cs.CL↗

arXiv2023

A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the Input is Under-Specified?

As text-to-image systems continue to grow in popularity with the general public, questions have arisen about bias and diversity in the generated images. Here, we investigate properties of images generated in response to prompts which are visually under-specified, but contain salient social attributes (e.g., 'a portrait of a threatening person' versus 'a portrait of a friendly person'). Grounding our work in social cognition theory, we find that in many cases, images contain similar demographic biases to those reported in the stereotype literature. However, trends are inconsistent across different models and further investigation is warranted.

cs.CY↗

arXiv2022

Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Information

Previous works on the fairness of toxic language classifiers compare the output of models with different identity terms as input features but do not consider the impact of other important concepts present in the context. Here, besides identity terms, we take into account high-level latent features learned by the classifier and investigate the interaction between these features and identity terms. For a multi-class toxic language classifier, we leverage a concept-based explanation framework to calculate the sensitivity of the model to the concept of sentiment, which has been used before as a salient feature for toxic language detection. Our results show that although for some classes, the classifier has learned the sentiment information as expected, this information is outweighed by the influence of identity terms as input features. This work is a step towards evaluating procedural fairness, where unfair processes lead to unfair outcomes. The produced knowledge can guide debiasing techniques to ensure that important concepts besides identity terms are well-represented in training datasets.

cs.CL↗

arXiv2022

Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models

Motivations for methods in explainable artificial intelligence (XAI) often include detecting, quantifying and mitigating bias, and contributing to making machine learning models fairer. However, exactly how an XAI method can help in combating biases is often left unspecified. In this paper, we briefly review trends in explainability and fairness in NLP research, identify the current practices in which explainability methods are applied to detect and mitigate bias, and investigate the barriers preventing XAI methods from being used more widely in tackling fairness issues.

cs.CL↗

arXiv2022

Does Moral Code Have a Moral Code? Probing Delphi's Moral Philosophy

In an effort to guarantee that machine learning model outputs conform with human moral values, recent work has begun exploring the possibility of explicitly training models to learn the difference between right and wrong. This is typically done in a bottom-up fashion, by exposing the model to different scenarios, annotated with human moral judgements. One question, however, is whether the trained models actually learn any consistent, higher-level ethical principles from these datasets -- and if so, what? Here, we probe the Allen AI Delphi model with a set of standardized morality questionnaires, and find that, despite some inconsistencies, Delphi tends to mirror the moral principles associated with the demographic groups involved in the annotation process. We question whether this is desirable and discuss how we might move forward with this knowledge.

cs.CY↗

arXiv2022

Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection

We present a novel feature attribution method for explaining text classifiers, and analyze it in the context of hate speech detection. Although feature attribution models usually provide a single importance score for each token, we instead provide two complementary and theoretically-grounded scores -- necessity and sufficiency -- resulting in more informative explanations. We propose a transparent method that calculates these values by generating explicit perturbations of the input text, allowing the importance scores themselves to be explainable. We employ our method to explain the predictions of different hate speech detection models on the same set of curated examples from a test suite, and show that different values of necessity and sufficiency for identity terms correspond to different kinds of false positive errors, exposing sources of classifier bias against marginalized groups.

cs.CL↗