Related papers: Debate or Vote: Which Yields Better Decisions in M…
In multi-agent debate (MAD) systems, performance gains are often reported; however, because the debate protocol (e.g., number of agents, rounds, and aggregation rule) is typically held fixed while model-related factors vary, it is difficult…
Large language models (LLMs) remain unreliable for high-stakes claim verification due to hallucinations and shallow reasoning. While retrieval-augmented generation (RAG) and multi-agent debate (MAD) address this, they are limited by…
Multi-agent debate has emerged as a promising approach for improving LLM reasoning on ground-truth tasks, yet current methodologies face certain structural limitations: debate tends to induce a martingale over belief trajectories, majority…
Large language model multi-agent systems (LLM-MAS) offer a promising paradigm for harnessing collective intelligence to achieve more advanced forms of AI behaviour. While recent studies suggest that LLM-MAS can outperform LLM single-agent…
Multi-agent debate - multiple instances of large language models discussing problems in turn-based interaction - has shown promise for solving knowledge and reasoning tasks. However, these methods show limitations when solving complex…
Large Language Models (LLMs) need to adapt their predictions to diverse cultural contexts to benefit diverse communities across the world. While previous efforts have focused on single-LLM, single-turn approaches, we propose to exploit the…
We introduce RedDebate, a novel multi-agent debate framework that provides the foundation for Large Language Models (LLMs) to identify and mitigate their unsafe behaviours. Existing AI safety approaches often rely on costly human evaluation…
In today's digital environment, the rapid propagation of fake news via social networks poses significant social challenges. Most existing detection methods either employ traditional classification models, which suffer from low…
Large Language Models (LLMs) have shown impressive capabilities in various applications, but they still face various inconsistency issues. Existing works primarily focus on the inconsistency issues within a single LLM, while we…
Large Language Models (LLMs) often produce answers with a single chain-of-thought, which restricts their ability to explore reasoning paths or self-correct flawed outputs in complex tasks. In this paper, we introduce MALT (Multi-Agent LLM…
We propose MADS (Multi-Agent Dialogue Simulation), a scalable framework for generating persuasive multi-turn dialogues via agent self-play. MADS employs three coordinated agents: User Agents designed to simulate diverse persona-driven…
This paper develops a natural-language agent-based model of argumentation (ABMA). Its artificial deliberative agents (ADAs) are constructed with the help of so-called neural language models recently developed in AI and computational…
We test the robustness of debate as a method of scalable oversight by training models to debate with data generated via self-play. In a long-context reading comprehension task, we find that language model based evaluators answer questions…
Detecting persuasion in argumentative text is a challenging task with important implications for understanding human communication. This work investigates the role of persuasion strategies - such as Attack on reputation, Distraction, and…
As Large Language Models (LLMs) gain expertise across diverse domains and modalities, scalable oversight becomes increasingly challenging, particularly when their capabilities may surpass human evaluators. Debate has emerged as a promising…
Large Language Models (LLMs) demonstrate strong conversational abilities. In this Working Paper, we study them in the context of debating in two ways: their ability to perform in a structured debate along with a dataset of arguments to use…
Fact-checking research has extensively explored verification but less so the generation of natural-language explanations, crucial for user trust. While Large Language Models (LLMs) excel in text generation, their capability for producing…
Scalable oversight protocols aim to enable humans to accurately supervise superhuman AI. In this paper we study debate, where two AI's compete to convince a judge; consultancy, where a single AI tries to convince a judge that asks…
One of the most challenging forms of misinformation involves pairing images with misleading text to create false narratives. Existing AI-driven detection systems often require domain-specific finetuning, limiting generalizability, and offer…
In recent years, large language models have shown exceptional performance in fulfilling diverse human needs. However, their training data can introduce harmful content, underscoring the necessity for robust value alignment. Mainstream…