5 papers
Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation
Erfan Baghaei Potraghloo, Seyedarmin Azizi, Souvik Kundu +1
Large language models (LLMs), despite their impressive performance across a wide range of tasks, often struggle to balance two competing objectives in open-ended text generation: f…
One Token Away from Collapse: The Fragility of Instruction-Tuned Helpfulness
Erfan Baghaei Potraghloo, Seyedarmin Azizi, Souvik Kundu +1
Instruction-tuned large language models produce helpful, structured responses, but how robust is this helpfulness under trivial constraints? We show that simple lexical constraints…
SkipKV: Selective Skipping of KV Generation and Storage for Efficient Inference with Large Reasoning Models
Jiayi Tian, Seyedarmin Azizi, Yequan Zhao +7
Large reasoning models (LRMs) often incur significant key-value (KV) cache overhead, due to their linear growth with the verbose chain-of-thought (CoT) reasoning. This incurs both…
Power-SMC: Low-Latency Sequence-Level Power Sampling for Training-Free LLM Reasoning
Seyedarmin Azizi, Erfan Baghaei Potraghloo, Minoo Ahmadi +2
Many recent reasoning gains in large language models can be explained as distribution sharpening: biasing generation toward high-likelihood trajectories already supported by the pr…
Activation Steering for Chain-of-Thought Compression
Seyedarmin Azizi, Erfan Baghaei Potraghloo, Massoud Pedram
Large language models (LLMs) excel at complex reasoning when they include intermediate steps, known as "chains of thought" (CoTs). However, these rationales are often overly verbos…