PromptNCE: Conditional Probabilities and PMI Using Only LLMs and Contrastive Estimation Prompts

arXiv:2605.21776 · cs.CL · Submitted 2026-05-20 · Read on arXiv

cs.CL

Submitted: 2026-05-20

Updated: 2026-09-01

Comments: Camera-ready version for COLM 2026

Code: https://github.com/google-research/google-research

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 11× in this paper · explained in 2 episodes
• Calibration — 10× in this paper · explained in 7 episodes
• Feature Selection — 2× in this paper · explained in 4 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• LLM-as-a-Judge — 2× in this paper · explained in 3 episodes
• Representation Learning — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Pointwise Mutual Information (PMI) — 1× in this paper · explained in 3 episodes
• Predictive Coding — 1× in this paper · explained in 2 episodes
• Quantifying Uncertainty — 1× in this paper · explained in 5 episodes

Sources

• From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge
• LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
• Opening the Black Box of Deep Neural Networks via Information
• Representation Learning with Contrastive Predictive Coding
• Calibrating Verbalized Probabilities for Large Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering