This repository provides the code for the paper "Language Models Represent Beliefs of Self and Others". It shows that LLMs internally represent beliefs of themselves and other agents, and manipulating these representations can significantly impact their Theory of Mind reasoning capabilities.
conda create -n lm python=3.8 anaconda
conda activate lm
# Please install PyTorch according to your CUDA version.
conda install pytorch torchvision torchaudio pytorch-cuda=11.6 -c pytorch -c nvidia
pip install -r requirements.txt
Then download the language models (e.g. Mistral-7B-Instruct-v0.2, deepseek-llm-7b-chat) to models/. You can also specify the file paths in lm_paths.json.
sh scripts/save_reps.sh 0_forward belief
sh scripts/save_reps.sh 0_forward action
sh scripts/save_reps.sh 0_backward beliefBinary:
python probe.py --belief=protagonist --dynamic=0_forward --variable belief
python probe.py --belief=oracle --dynamic=0_forward --variable belief
python probe.py --belief=protagonist --dynamic=0_forward --variable action
python probe.py --belief=oracle --dynamic=0_forward --variable action
python probe.py --belief=protagonist --dynamic=0_backward --variable belief
python probe.py --belief=oracle --dynamic=0_backward --variable beliefMultinomial:
python probe_multinomial.py --dynamic=0_forward --variable belief
python probe_multinomial.py --dynamic=0_forward --variable action
python probe_multinomial.py --dynamic=0_backward --variable beliefsh scripts/0_forward_belief.sh
sh scripts/0_forward_action.sh
sh scripts/0_backward_belief.shIntervention for the Forward Belief task:
sh scripts/0_forward_belief_interv_oracle.sh
sh scripts/0_forward_belief_interv_protagonist.sh
sh scripts/0_forward_belief_interv_o0p1.shCross-task intervention:
sh scripts/cross_0_forward_belief_to_forward_action_interv_o0p1.sh
sh scripts/cross_0_forward_belief_to_backward_belief_interv_o0p1.sh@inproceedings{zhu2024language,
title={Language Models Represent Beliefs of Self and Others},
author={Zhu, Wentao and Zhang, Zhining and Wang, Yizhou},
booktitle={Forty-first International Conference on Machine Learning},
year={2024}
}
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent