Most | Son The Nguyen

Response Engineering for Training-Free Alignment of LLMs

Tue, 11 Aug 2026 18:00:00 +0000

This hands-on tutorial explores response engineering techniques that improve language-model outputs at inference time, including Best-of-N selection, self-consistency, Reflexion, and Mixture-of-Agents.

This notebook was developed and curated by Son The Nguyen for the NAIRR 2026 Training-Free Alignment of LLMs tutorial.

Guided Decoding for Training-Free Alignment of LLMs

Tue, 11 Aug 2026 17:00:00 +0000

This hands-on tutorial introduces inference-time methods for aligning language model behavior without modifying model weights. It begins with standard decoding strategies, including greedy decoding, beam search, temperature sampling, and top-k/top-p sampling, and then develops guided decoding with custom logits processors.

This notebook was developed and curated by Son The Nguyen for the NAIRR 2026 Training-Free Alignment of LLMs tutorial.

Prompt Engineering for Training-Free Alignment of LLMs

Tue, 11 Aug 2026 16:00:00 +0000

This hands-on tutorial introduces programmatic prompt engineering with DSPy, from hosting a local language model to defining signatures and modules, evaluating a reasoning pipeline, and optimizing it with MIPROv2.

This notebook was developed and curated by Tommy Cheng for the NAIRR 2026 Training-Free Alignment of LLMs tutorial.