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

To improve the reasoning and question-answering capabilities of Large Language Models (LLMs), several multi-agent approaches have been introduced. While these methods enhance performance, the application of collective intelligence-based…

Multi-agent debate (MAD) has gained significant attention as a promising line of research to improve the factual accuracy and reasoning capabilities of large language models (LLMs). Despite its conceptual appeal, current MAD research…

Multi-agent debate (MAD) systems improve LLM reasoning through iterative deliberation, but remain vulnerable to debate collapse, a failure type where final agent decisions are compromised on erroneous reasoning. Existing methods lack…

Current adversarial attack algorithms, where an adversary changes a text to fool a victim model, have been repeatedly shown to be effective against text classifiers. These attacks, however, generally assume that the victim model is…

Multi-agent debate (MAD) is an emerging approach to improving the reasoning capabilities of large language models (LLMs). Existing MAD methods rely on multiple rounds of interaction among agents to reach consensus, and the final output is…

Foundation model-based agents are increasingly used to automate complex tasks, enhancing efficiency and productivity. However, their access to sensitive resources and autonomous decision-making also introduce significant security risks,…

Recent advances in Large Language Models (LLMs) have enabled multi-agent systems that simulate real-world interactions with near-human reasoning. While previous studies have extensively examined biases related to protected attributes such…

When people reason about cause and effect, they often consider many competing "what if" scenarios before deciding which explanation fits best. Analogously, advanced language models capable of causal inference can consider multiple…

As natural language generation (NLG) models have become prevalent, systematically assessing the quality of machine-generated texts has become increasingly important. Recent studies introduce LLM-based evaluators that operate as…

Recent studies in multi-agent communicative reinforcement learning (MACRL) have demonstrated that multi-agent coordination can be greatly improved by allowing communication between agents. Meanwhile, adversarial machine learning (ML) has…

Large language models (LLMs) have recently demonstrated impressive capabilities in reasoning tasks. Currently, mainstream LLM reasoning frameworks predominantly focus on scaling up inference-time sampling to enhance performance. In…

Modern large language models (LLMs) like ChatGPT have shown remarkable performance on general language tasks but still struggle on complex reasoning tasks, which drives the research on cognitive behaviors of LLMs to explore human-like…

Argument Mining (AM) is a foundational technology for automated writing evaluation, yet traditional supervised approaches rely heavily on expensive, domain-specific fine-tuning. While Large Language Models (LLMs) offer a training-free…

Large language models (LLMs) are susceptible to red teaming attacks, which can induce LLMs to generate harmful content. Previous research constructs attack prompts via manual or automatic methods, which have their own limitations on…

In an era where single large language models have dominated the landscape of artificial intelligence for years, multi-agent systems arise as new protagonists in conversational task-solving. While previous studies have showcased their…

Multi-agent debate (MAD) has recently emerged as a promising framework for improving the reasoning performance of large language models (LLMs). Yet, whether LLM agents can genuinely engage in deliberative reasoning, beyond simple ensembling…

Multi-agent debate (MAD) systems leverage collaborative interactions among large language models (LLMs) agents to improve reasoning capabilities. While recent studies have focused on increasing the accuracy and scalability of MAD systems,…

Lack of moderation in online communities enables participants to incur in personal aggression, harassment or cyberbullying, issues that have been accentuated by extremist radicalisation in the contemporary post-truth politics scenario. This…

Recent advances in large language models (LLMs) have raised concerns about jailbreaking attacks, i.e., prompts that bypass safety mechanisms. This paper investigates the use of multi-agent LLM systems as a defence against such attacks. We…

Two ways has been discussed to unlock the reasoning capability of a large language model. The first one is prompt engineering and the second one is to combine the multiple inferences of large language models, or the multi-agent discussion.…