Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
Chopthin-Consensus Power Sampling: A Diversity-Preserving Approach to LLM Decoding
Minoo Ahmadi, Seyedarmin Azizi, Erfan Baghaei Potraghloo +2
Inference-time power sampling via Sequential Monte Carlo (SMC) can substantially improve large language model (LLM) reasoning without requiring post-training. However, many existin…
cs.CL2026
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…
cs.CL2025
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…