2 papers
cs.CL2026
Representation of syntax in LLMs through the lens of linear distance and similarity-aware entropy
Juan Pablo Vigneaux, Mary Kennedy, Khalil Iskarous +2
Structural probes were introduced by Hewitt and Manning to reconstruct syntactic trees from a neural language model's latent representations. They are evaluated by calculating the…
cs.CL2026
Causal Interventions on Continuous Variables: A Case Study on Verb Bias in Steering Vectors for In-Context Learning
Zhenghao Herbert Zhou, R. Thomas McCoy, Robert Frank
Causal interventions in language model representations have largely targeted discrete features, like grammatical number. However, language models must also make use of features tha…