Related papers: Self-playing Adversarial Language Game Enhances LL…
Game environments provide rich, controllable settings that stimulate many aspects of real-world complexity. As such, game agents offer a valuable testbed for exploring capabilities relevant to Artificial General Intelligence. Recently, the…
Role-playing is an easy task for Large Language Models (LLMs), as they are skilled at simulating human behaviors. Many current studies have enabled LLMs to generate responses in the tone of a specific role by fine-tuning the models or using…
The integration of Large Language Models (LLMs) into healthcare applications offers promising advancements in medical diagnostics, treatment recommendations, and patient care. However, the susceptibility of LLMs to adversarial attacks poses…
We present a Lipreading system, i.e. a speech recognition system using only visual features, which uses domain-adversarial training for speaker independence. Domain-adversarial training is integrated into the optimization of a lipreader…
We study the problem of learning classifiers robust to universal adversarial perturbations. While prior work approaches this problem via robust optimization, adversarial training, or input transformation, we instead phrase it as a…
The proliferation of large language models (LLMs) has sparked widespread and general interest due to their strong language generation capabilities, offering great potential for both industry and research. While previous research delved into…
Reinforcement learning based dialogue policies are typically trained in interaction with a user simulator. To obtain an effective and robust policy, this simulator should generate user behaviour that is both realistic and varied. Current…
The increasing integration of Large Language Models (LLMs) into society necessitates robust defenses against vulnerabilities from jailbreaking and adversarial prompts. This project proposes a recursive framework for enhancing the resistance…
We introduce LLM CHESS, an evaluation framework designed to probe the generalization of reasoning and instruction-following abilities in large language models (LLMs) through extended agentic interaction in the domain of chess. We rank over…
Mitigating hallucinations of Large Vision Language Models,(LVLMs) is crucial to enhance their reliability for general-purpose assistants. This paper shows that such hallucinations of LVLMs can be significantly exacerbated by preceding…
Are Large Language Models (LLMs) a new form of strategic intelligence, able to reason about goals in competitive settings? We present compelling supporting evidence. The Iterated Prisoner's Dilemma (IPD) has long served as a model for…
LLM agents are known to deviate from Nash equilibria in strategic interactions, but nobody has looked inside the model to understand why, or asked whether the deviation can be reversed. We do both. Working with four open-source models…
Deep reinforcement learning (RL) policies are known to be vulnerable to adversarial perturbations to their observations, similar to adversarial examples for classifiers. However, an attacker is not usually able to directly modify another…
At the beginning of 2022, a simplistic word-guessing game took the world by storm and was further adapted to many languages beyond the original English version. In this paper, we examine the strategies of daily word-guessing game players…
Large Language Models (LLMs) have shown remarkable promise in communicating with humans. Their potential use as artificial partners with humans in sociological experiments involving conversation is an exciting prospect. But how viable is…
Large Language Models (LLMs) can justify or critique their predictions through discussions with other models or humans, thereby enriching their intrinsic understanding of instances. While proactive discussions in the inference phase have…
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…
This study investigates the behaviors of Large Language Models (LLMs) when faced with conflicting prompts versus their internal memory. This will not only help to understand LLMs' decision mechanism but also benefit real-world applications,…
Large Language Models (LLMs) are becoming vital tools that help us solve and understand complex problems by acting as digital assistants. LLMs can generate convincing explanations, even when only given the inputs and outputs of these…
Hallucination continues to pose a major obstacle in the reasoning capabilities of large language models (LLMs). Although the Multi-Agent Debate (MAD) paradigm offers a promising solution by promoting consensus among multiple agents to…