Related papers: Combating Adversarial Attacks with Multi-Agent Deb…

Red-teaming is a common practice for mitigating unsafe behaviors in Large Language Models (LLMs), which involves thoroughly assessing LLMs to identify potential flaws and addressing them with responsible and accurate responses. While…

With the recent surge of language models in different applications, attention to safety and robustness of these models has gained significant importance. Here we introduce a joint framework in which we simultaneously probe and improve the…

Warning: this paper contains content that maybe offensive or upsetting. Recent research in Natural Language Processing (NLP) has advanced the development of various toxicity detection models with the intention of identifying and mitigating…

Language Model Models (LLMs) have improved dramatically in the past few years, increasing their adoption and the scope of their capabilities over time. A significant amount of work is dedicated to ``model alignment'', i.e., preventing LLMs…

Multi-agent systems - systems with multiple independent AI agents working together to achieve a common goal - are becoming increasingly prevalent in daily life. Drawing inspiration from the phenomenon of human group social influence, we…

Adversarial attacking aims to fool deep neural networks with adversarial examples. In the field of natural language processing, various textual adversarial attack models have been proposed, varying in the accessibility to the victim model.…

As large language models (LLMs) are increasingly deployed as black-box components in real-world applications, red teaming has become essential for identifying potential risks. It tests LLMs with adversarial prompts to uncover…

Strategic interaction in adversarial domains such as law, diplomacy, and negotiation is mediated by language, yet most game-theoretic models abstract away the mechanisms of persuasion that operate through discourse. We present the Strategic…

LLM-as-Judge has emerged as a scalable alternative to human evaluation, enabling large language models (LLMs) to provide reward signals in trainings. While recent work has explored multi-agent extensions such as multi-agent debate and…

Social media has evolved into a complex multimodal environment where text, images, and other signals interact to shape nuanced meanings, often concealing harmful intent. Identifying such intent, whether sarcasm, hate speech, or…

The design of better automated dialogue evaluation metrics offers the potential of accelerate evaluation research on conversational AI. However, existing trainable dialogue evaluation models are generally restricted to classifiers trained…

Language models are increasingly deployed in interactive online environments, from personal chat assistants to domain-specific agents, raising questions about their cooperative and competitive behavior in multi-party settings. While prior…

Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful…

Communicating in natural language is a powerful tool in multi-agent settings, as it enables independent agents to share information in partially observable settings and allows zero-shot coordination with humans. However, most prior works…

Task oriented language understanding in dialog systems is often modeled using intents (task of a query) and slots (parameters for that task). Intent detection and slot tagging are, in turn, modeled using sentence classification and word…

We introduce AgenticSimLaw, a role-structured, multi-agent debate framework that provides transparent and controllable test-time reasoning for high-stakes tabular decision-making tasks. Unlike black-box approaches, our courtroom-style…

Safety evaluation of large language models (LLMs) increasingly relies on LLM-as-a-judge pipelines, but strong judges can still be expensive to use at scale. We study whether structured multi-agent debate can improve judge reliability while…

Large Language Models (LLMs) have demonstrated potential in automating scientific ideation, yet current approaches relying on iterative prompting or complex multi-agent architectures often suffer from hallucination or computational…

Phishing attacks remain a critical cybersecurity threat. Attackers constantly refine their methods, making phishing emails harder to detect. Traditional detection methods, including rule-based systems and supervised machine learning models,…

Nowadays, single Large Language Model (LLM) struggles with critical issues such as hallucination and inadequate reasoning abilities. To mitigate these issues, Multi-Agent Debate (MAD) has emerged as an effective strategy, where LLM agents…