For What Reason? Interpreting Models' Encoding of Causation and Antithesis

Title:For What Reason? Interpreting Models' Encoding of Causation and Antithesis

Abstract:Discourse relations provide document structure, critical to language understanding and enabling language model performance and ethicality. In this work, we investigate how instruction-tuned Transformer models (LLaMA and Mistral) encode discourse relations in English, with a particular focus on the contrasting relations of causation and antithesis. Framing the task as a next-token prediction task and applying a suite of interpretability techniques to test model internals, our findings show that certain early layers make predictive decisions at mid-sequence tokens, while some mid-level layers finalize their decisions closer to the last token. Most of the remaining layers primarily propagate earlier decisions rather than actively influencing them. Additionally, we observe that some layers exhibit a preference for one answer over alternatives, suggesting asymmetric representation of discourse-based reasoning.\footnote{Our code is available at this https URL}

Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

arXiv:2607.18570 [cs.CL]

(or arXiv:2607.18570v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2607.18570 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.