The paper claims that regret in LLMs is encoded by interacting neuron groups detectable in the final hidden layer, using new S-CDI, RDS, and GIC metrics.
Probing for Constituency Structure in Neural Language Models
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
In this paper, we investigate to which extent contextual neural language models (LMs) implicitly learn syntactic structure. More concretely, we focus on constituent structure as represented in the Penn Treebank (PTB). Using standard probing techniques based on diagnostic classifiers, we assess the accuracy of representing constituents of different categories within the neuron activations of a LM such as RoBERTa. In order to make sure that our probe focuses on syntactic knowledge and not on implicit semantic generalizations, we also experiment on a PTB version that is obtained by randomly replacing constituents with each other while keeping syntactic structure, i.e., a semantically ill-formed but syntactically well-formed version of the PTB. We find that 4 pretrained transfomer LMs obtain high performance on our probing tasks even on manipulated data, suggesting that semantic and syntactic knowledge in their representations can be separated and that constituency information is in fact learned by the LM. Moreover, we show that a complete constituency tree can be linearly separated from LM representations.
citation-role summary
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
REJECT 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
The Compositional Architecture of Regret in Large Language Models
The paper claims that regret in LLMs is encoded by interacting neuron groups detectable in the final hidden layer, using new S-CDI, RDS, and GIC metrics.