Paper Reading : LLMs as Theory of Mind Aware Generative Agents with Counterfactual Reflection
Details
This week, we will walk through and discuss the paper:
Large Language Models as Theory of Mind Aware Generative Agents with Counterfactual Reflection
[https://arxiv.org/abs/2501.15355]
Abstract of the paper:
Recent studies have increasingly demonstrated that large language models (LLMs) possess significant theory of mind (ToM) capabilities, showing the potential for simulating the tracking of mental states in generative agents. In this study, we propose a novel paradigm called ToM-agent, designed to empower LLMs-based generative agents to simulate ToM in open-domain conversational interactions. ToM-agent disentangles the confidence from mental states, facilitating the emulation of an agent's perception of its counterpart's mental states, such as beliefs, desires, and intentions (BDIs). Using past conversation history and verbal reflections, ToM-Agent can dynamically adjust counterparts' inferred BDIs, along with related confidence levels. We further put forth a counterfactual intervention method that reflects on the gap between the predicted responses of counterparts and their real utterances, thereby enhancing the efficiency of reflection. Leveraging empathetic and persuasion dialogue datasets, we assess the advantages of implementing the ToM-agent with downstream tasks, as well as its performance in both the first-order and the \textit{second-order} ToM. Our findings indicate that the ToM-agent can grasp the underlying reasons for their counterpart's behaviors beyond mere semantic-emotional supporting or decision-making based on common sense, providing new insights for studying large-scale LLMs-based simulation of human social behaviors.
----------------
About SupportVectors AI Meetup:
We are a group of applied AI practitioners and enthusiasts who have formed a collective learning community. Every Wednesday evening at PM PST, we hold our research paper reading seminar covering an AI topic. One member carefully explains the paper, making it more accessible to a broader audience. Then, we follow this reading with a more informal discussion and socializing.
You are welcome to join this in person or over Zoom. SupportVectors is an AI training lab located in Fremont, CA, close to Tesla and easily accessible by road and BART. We follow the weekly sessions with snacks, soft drinks, and informal discussions.
You are welcome to join this in person or over Zoom (https://us02web.zoom.us/meeting/register/tZUvf-uvrTwvHdP9B-vE03j3BapgRypn64CS). SupportVectors is an AI training lab located in Fremont, CA, close to Tesla and easily accessible by road and BART. We follow the weekly sessions with snacks, soft drinks, and informal discussions.
Speaker :
Krishnan Ramaswamy
LinkedIn: krishnan-ramaswamy
Gen AI Product Development & Principal Architect @ Cisco for, AI, ML, and Gen AI-enabled computer networking products & solutions.
In my current role as Gen AI Product Owner and Principal Architect at Cisco, I spearhead the innovation of AI/ML-enabled solutions within the Customer Experience portfolio, concentrating on Data Center and Security domains. Our team's initiatives have led to the identification of transformative Gen AI solutions, significantly enhancing productivity across support teams, customers, and partners.
I take pride in leading the development of advanced AI technologies, such as Conversational AI Search and Custom LLMs-based applications, which have been instrumental in advancing Cisco's product configuration and deployment design. The strategic integration of next-generation products and services under my guidance has driven meaningful advancements, positioning us at the forefront of the industry's evolution.