2024-06-25 15:04:12 +02:00
|
|
|
<div align="center">
|
|
|
|
|
<h1> Benchmarking Mental State Representations in Language Models </h1>
|
2024-06-25 14:43:23 +02:00
|
|
|
|
2024-06-25 15:04:12 +02:00
|
|
|
**[Matteo Bortoletto][1], [Constantin Ruhdorfer][5], [Lei Shi][2], [Andreas Bulling][3]** <br> <br>
|
|
|
|
|
**ICML 2024 Workshop on Mechanistic Interpretability, Vienna, Austria** <br>
|
|
|
|
|
**[[Paper][4]]**
|
|
|
|
|
|
|
|
|
|
</div>
|
|
|
|
|
|
|
|
|
|
# Citation
|
|
|
|
|
|
|
|
|
|
```bibtex
|
|
|
|
|
@inproceedings{
|
|
|
|
|
bortoletto2024benchmarking,
|
|
|
|
|
title={Benchmarking Mental State Representations in Language Models},
|
|
|
|
|
author={Matteo Bortoletto and Constantin Ruhdorfer and Lei Shi and Andreas Bulling},
|
|
|
|
|
booktitle={ICML 2024 Workshop on Mechanistic Interpretability},
|
|
|
|
|
year={2024},
|
|
|
|
|
url={https://openreview.net/forum?id=yEwEVoH9Be}
|
|
|
|
|
}
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Under construction
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
[1]: https://mattbortoletto.github.io/
|
|
|
|
|
[2]: https://perceptualui.org/people/shi/
|
|
|
|
|
[3]: https://perceptualui.org/people/bulling/
|
|
|
|
|
[4]: https://openreview.net/forum?id=yEwEVoH9Be
|
|
|
|
|
[5]: https://perceptualui.org/people/ruhdorfer/
|
