Tommaso Caselli
@tommasoc80.bsky.social
assistant professor at GroNLP (@unigroningen.bsky.social) - working on #storylines, #misinformation, and #hatespeech all in #NLP 🍉
and we also have @gronlp.bsky.social stickers 🤩
September 18, 2025 at 4:29 PM
and we also have @gronlp.bsky.social stickers 🤩
Reposted by Tommaso Caselli
Reposted by Tommaso Caselli
what this means it that we don't have a good mental model of how different steps in the LLM generation process depend on each other, and what are the causal relations that make it tick. which in turn means that LLM's explanations might be "transparent", but also that we fail to interpret them.
August 27, 2025 at 9:36 PM
what this means it that we don't have a good mental model of how different steps in the LLM generation process depend on each other, and what are the causal relations that make it tick. which in turn means that LLM's explanations might be "transparent", but also that we fail to interpret them.
Reposted by Tommaso Caselli
the test is very simple: given an AI reasoning text broken into steps, we highlight one step as the target, and then ask you to identify the one-out-of-four preceding steps that we choose, which, if removed, will change the target step. turns out this is really hard.
August 27, 2025 at 9:34 PM
the test is very simple: given an AI reasoning text broken into steps, we highlight one step as the target, and then ask you to identify the one-out-of-four preceding steps that we choose, which, if removed, will change the target step. turns out this is really hard.
📝camera-ready and 🧑💻Git link will be available soon
August 22, 2025 at 8:32 AM
📝camera-ready and 🧑💻Git link will be available soon