Summary of Tom-lm: Delegating Theory Of Mind Reasoning to External Symbolic Executors in Large Language Models, by Weizhi Tang et al.
ToM-LM: Delegating Theory of Mind Reasoning to External Symbolic Executors in Large Language Models
by Weizhi Tang, Vaishak Belle
First submitted to arxiv on: 23 Apr 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed approach, ToM-LM, leverages an external symbolic executor, SMCDEL model checker, and fine-tuning to improve the Theory of Mind (ToM) reasoning ability of Large Language Models (LLMs). Specifically, an LLM is fine-tuned through pairs of natural language and symbolic formulation representation of ToM problems, followed by generation of a symbolic formulation using a one-shot in-context example. The generated symbolic formulation is then executed by SMCDEL to perform transparent and verifiable ToM reasoning, yielding a significant improvement over constructed baselines. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary ToM-LM helps computers better understand people’s thoughts and feelings. This is important because current language models are not very good at this. The new approach uses an external tool called SMCDEL model checker, which can execute symbolic formulas to reason about beliefs. This allows the language model to generate a formula that SMCDEL can use to make decisions based on what someone might be thinking or feeling. In experiments, ToM-LM performed better than other methods. |
Keywords
» Artificial intelligence » Fine tuning » Language model » One shot
