Stefan F. Schouten
@stefanfs.me
PhD candidate CLTL VU Amsterdam
Prev. Research Intern Huawei
stefanfs.me
Prev. Research Intern Huawei
stefanfs.me
How do you know your contrastive probing data identifies a unique feature?
How can we identify directions that model combinations of features?
We propose Contrastive Eigenproblems to tackle both of these issues.
Come see the poster at the MechInterp Workshop @ NeurIPS this sunday!
How can we identify directions that model combinations of features?
We propose Contrastive Eigenproblems to tackle both of these issues.
Come see the poster at the MechInterp Workshop @ NeurIPS this sunday!
December 3, 2025 at 3:33 PM
How do you know your contrastive probing data identifies a unique feature?
How can we identify directions that model combinations of features?
We propose Contrastive Eigenproblems to tackle both of these issues.
Come see the poster at the MechInterp Workshop @ NeurIPS this sunday!
How can we identify directions that model combinations of features?
We propose Contrastive Eigenproblems to tackle both of these issues.
Come see the poster at the MechInterp Workshop @ NeurIPS this sunday!
Reposted by Stefan F. Schouten
📢 Our paper on 'Truth-value Judgment in LLMs' was accepted to @colmweb.org #COLM2025!
In this paper, we investigate how LLMs keep track of the truth of sentences when reasoning.
In this paper, we investigate how LLMs keep track of the truth of sentences when reasoning.
July 14, 2025 at 2:55 PM
📢 Our paper on 'Truth-value Judgment in LLMs' was accepted to @colmweb.org #COLM2025!
In this paper, we investigate how LLMs keep track of the truth of sentences when reasoning.
In this paper, we investigate how LLMs keep track of the truth of sentences when reasoning.
📢 Our paper on 'Truth-value Judgment in LLMs' was accepted to @colmweb.org #COLM2025!
In this paper, we investigate how LLMs keep track of the truth of sentences when reasoning.
In this paper, we investigate how LLMs keep track of the truth of sentences when reasoning.
July 14, 2025 at 2:55 PM
📢 Our paper on 'Truth-value Judgment in LLMs' was accepted to @colmweb.org #COLM2025!
In this paper, we investigate how LLMs keep track of the truth of sentences when reasoning.
In this paper, we investigate how LLMs keep track of the truth of sentences when reasoning.