3 papers
cs.CL2026
When Chain-of-Thought Fails, the Solution Hides in the Hidden States
Houman Mehrafarin, Amit Parekh, Ioannis Konstas
Whether intermediate reasoning is computationally useful or merely explanatory depends on whether chain-of-thought (CoT) tokens contain task-relevant information. We present a mech…
cs.CL2024
Reasoning or a Semblance of it? A Diagnostic Study of Transitive Reasoning in LLMs
Houman Mehrafarin, Arash Eshghi, Ioannis Konstas
Evaluating Large Language Models (LLMs) on reasoning benchmarks demonstrates their ability to solve compositional questions. However, little is known of whether these models engage…
cs.CL2022
On the Importance of Data Size in Probing Fine-tuned Models
Houman Mehrafarin, Sara Rajaee, Mohammad Taher Pilehvar
Several studies have investigated the reasons behind the effectiveness of fine-tuning, usually through the lens of probing. However, these studies often neglect the role of the siz…