Evaluating Token Probabilities as Confidence Estimators in Human Behavior Simulations: A Case Study in Luxembourgish Next Like Prediction
cs.CL, cs.AI
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/huggingface/trl
Project page: https://evas-research.github.io
Terminology
Sources
- 8-bit Optimizers via Block-wise Quantization
- Language Models (Mostly) Know What They Know
- Ministral 3
- LuxEmbedder: A Cross-Lingual Approach to Enhanced Luxembourgish Sentence Embeddings
- Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation
- Can LLMs Think Like Consumers? Benchmarking Crowd-Level Reaction Reconstruction with ConsumerSimBench
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data