Federico Bianchi

Covering other langauges

6

https://github.com/MilaNLProc/contextualized-topic-models/blob/4fdf8d922500bd2c24f8df068e0f3c898ad85451/contextualized_topic_models/utils/preprocessing.py#L35 Need to fix this to support other languages

Startup script error

5

Hi! the `startup.sh` script is not able to connect to dbpedia-spotlight download endpoint (`http://spotlight.sztaki.hu/downloads/dbpedia-spotlight-latest.jar` seems not available at the moment). I downloaded spotlight manually, commented the relative lines in the...

Implement MACE-based agreement measures

Hi thanks for the great work! could I ask for the command used to run the evaluation on the https://github.com/EleutherAI/lm-evaluation-harness/? one that is running on any dataset is fine, I...

Currently, modifying a prompt requires a lot of work (basically, the best way is making a new game or reimporting the GameInterface). is there any way to simplify this?

we should avoid reloading the games everytime

if the palyer split the 100 in equal amounts, the outcome we save in the logs -50, 50. Needs to be 50,50.

https://github.com/vinid/rationality-llms/blob/afa933d51a2aa56367f4b09909098cde7b221de5/game/agents/chatgpt.py#L35 should this be checking for `in self.agent_name` instead of `role`?