Related papers: Self-Anchored Attention Model for Sample-Efficient…

Large Language Models are widely used for content moderation but often present certain over-sensitivity, leading to misclassification of benign content and rejecting safe user commands. While previous research attributes this issue…

With the increased awareness of situations of mental crisis and their societal impact, online services providing emergency support are becoming commonplace in many countries. Computational models, trained on discussions between help-seekers…

Using a sequence-to-sequence framework, many neural conversation models for chit-chat succeed in naturalness of the response. Nevertheless, the neural conversation models tend to give generic responses which are not specific to given…

Conventional methods of assessing attitudes towards climate change are limited in capturing authentic opinions, primarily stemming from a lack of context-specific assessment strategies and an overreliance on simplistic surveys. Game-based…

Language models pre-trained on large self-supervised corpora, followed by task-specific fine-tuning has become the dominant paradigm in NLP. These pre-training datasets often have a one-to-many structure--e.g. in dialogue there are many…

Studies have shown that toxic behavior can cause contributors to leave, and hinder newcomers' (especially from underrepresented communities) participation in Open Source Software (OSS) projects. Thus, detection of toxic language plays a…

Large Language Models (LLMs) have demonstrated superior performance in language understanding benchmarks. CALM, a popular approach, leverages linguistic priors of LLMs -- GPT-2 -- for action candidate recommendations to improve the…

Natural language processing (NLP) models are known to be vulnerable to backdoor attacks, which poses a newly arisen threat to NLP models. Prior online backdoor defense methods for NLP models only focus on the anomalies at either the input…

Language is often used strategically, particularly in high-stakes, adversarial settings, yet most work on pragmatics and LLMs centers on cooperativity. This leaves a gap in the systematic understanding of strategic communication in…

As Large Language Models (LLMs) increasingly operate as autonomous decision-makers in interactive and multi-agent systems and human societies, understanding their strategic behaviour has profound implications for safety, coordination, and…

Large Language Models (LLMs) have shown potential in simulating human behaviors and performing theory-of-mind (ToM) reasoning, a crucial skill for complex social interactions. In this study, we investigate the role of ToM reasoning in…

The growing deployment of large language model (LLM) based agents that interact with external environments has created new attack surfaces for adversarial manipulation. One major threat is indirect prompt injection, where attackers embed…

Hate speech on online platforms has been credibly linked to multiple instances of real world violence. This calls for an urgent need to understand how toxic content spreads and how it might be mitigated on online social networks, and…

Building an open-domain conversational agent is a challenging problem. Current evaluation methods, mostly post-hoc judgments of static conversation, do not capture conversation quality in a realistic interactive context. In this paper, we…

Online communities have gained considerable importance in recent years due to the increasing number of people connected to the Internet. Moderating user content in online communities is mainly performed manually, and reducing the workload…

Psychological measurement is essential for mental health, self-understanding, and personal development. Traditional methods, such as self-report scales and psychologist interviews, often face challenges with engagement and accessibility.…

User posts whose perceived toxicity depends on the conversational context are rare in current toxicity detection datasets. Hence, toxicity detectors trained on existing datasets will also tend to disregard context, making the detection of…

Communities typically capture homophily as people of the same community share many common features. This paper is motivated by the problem of community detection in social networks, as it can help improve our understanding of the network…

Large language models (LLMs) are increasingly explored as scalable tools for mental health counseling, yet evaluating their safety remains challenging due to the interactional and context-dependent nature of clinical harm. Existing…

The widespread adoption of Large Language Models (LLMs), exemplified by OpenAI's ChatGPT, brings to the forefront the imperative to defend against adversarial threats on these models. These attacks, which manipulate an LLM's output by…