4 papers
The Shape of Overthinking: Backtracking Bursts in Long Reasoning Traces
Navid Rezazadeh, Arash Gholami Davoodi
Reasoning models often generate long traces in which useful self-correction and unproductive revision are hard to distinguish. We study this distinction through backtracking dynami…
Geometry-Aware Decoding with Wasserstein-Regularized Truncation and Mass Penalties for Large Language Models
Arash Gholami Davoodi, Navid Rezazadeh, Seyed Pouyan Mousavi Davoudi +1
Large language models (LLMs) must balance diversity and creativity against logical coherence in open-ended generation. Existing truncation-based samplers are effective but largely…
Vertex-Softmax: Tight Transformer Verification via Exact Softmax Optimization
Navid Rezazadeh, Arash Gholami Davoodi
Certified verification of transformer attention requires bounding the softmax function over interval constraints on the pre-softmax scores. Existing verifiers relax softmax ndepend…
LLMs Are Not Intelligent Thinkers: Introducing Mathematical Topic Tree Benchmark for Comprehensive Evaluation of LLMs
Arash Gholami Davoodi, Seyed Pouyan Mousavi Davoudi, Pouya Pezeshkpour
Large language models (LLMs) demonstrate impressive capabilities in mathematical reasoning. However, despite these achievements, current evaluations are mostly limited to specific…