Cover Image

Bayesian Elicitation with LLMs: Model Size Helps, Extra "Reasoning" Doesn't Always

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hobor, Luka, Brcic, Mario, Kovac, Mihael, Poje, Kristijan
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AI-Assisted Unit Test Writing and Test-Driven Code Refactoring: A Case Study
by: Smolic, Ema, et al.
Published: (2026)

Comparative Analysis of Modern Machine Learning Models for Retail Sales Forecasting
by: Hobor, Luka, et al.
Published: (2025)

Order Doesn't Matter, But Reasoning Does: Training LLMs with Order-Centric Augmentation
by: He, Qianxi, et al.
Published: (2025)

Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism
by: Zhang, Haoxiang, et al.
Published: (2026)

One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs
by: He, Di, et al.
Published: (2026)

ChatGPT Doesn't Trust Chargers Fans: Guardrail Sensitivity in Context
by: Li, Victoria R., et al.
Published: (2024)

Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space
by: Verma, Gaurav, et al.
Published: (2024)

Infinite Width Models That Work: Why Feature Learning Doesn't Matter as Much as You Think
by: Sernau, Luke
Published: (2024)

Mask-Mediator-Wrapper architecture as a Data Mesh driver
by: Dončević, Juraj, et al.
Published: (2022)

Language Complexity and Speech Recognition Accuracy: Orthographic Complexity Hurts, Phonological Complexity Doesn't
by: Taguchi, Chihiro, et al.
Published: (2024)

Safe Reinforcement Learning in a Simulated Robotic Arm
by: Kovač, Luka, et al.
Published: (2023)

REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
by: Wang, Ziqiao, et al.
Published: (2025)

Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences
by: Falahati, Ali, et al.
Published: (2026)

Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
by: Cooper, A. Feder, et al.
Published: (2024)

MedCalc-Bench Doesn't Measure What You Think: A Benchmark Audit and the Case for Open-Book Evaluation
by: Krohn-Grimberghe, Artus
Published: (2026)

Revisiting Intermediate-Layer Matching in Knowledge Distillation: Layer-Selection Strategy Doesn't Matter (Much)
by: Yu, Zony, et al.
Published: (2025)

SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs
by: Lin, Jiacheng, et al.
Published: (2025)

Logic-Regularized Verifier Elicits Reasoning from LLMs
by: Wang, Xinyu, et al.
Published: (2026)

Self-Training Doesn't Flatten Language -- It Restructures It: Surface Markers Amplify While Deep Syntax Dies
by: Liu, Ming
Published: (2026)

MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs
by: Wu, Juncheng, et al.
Published: (2025)

Eliciting Better Multilingual Structured Reasoning from LLMs through Code
by: Li, Bryan, et al.
Published: (2024)

Triples and Knowledge-Infused Embeddings for Clustering and Classification of Scientific Documents
by: Arcan, Mihael
Published: (2025)

Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't
by: Dang, Quy-Anh, et al.
Published: (2025)

Eliciting Reasoning in Language Models with Cognitive Tools
by: Ebouky, Brown, et al.
Published: (2025)

Consciousness Doesn't Do That
by: Matthias Michel
Published: (2026)

Do Generated Data Always Help Contrastive Learning?
by: Wang, Yifei, et al.
Published: (2024)

Dead Code Doesn't Talk: Authentic Requirements Elicitation in Introductory Software Engineering
by: Berrezueta-Guzman, Santiago, et al.
Published: (2026)

Sherlock Holmes Doesn't Play Dice: The mathematics of uncertain reasoning when something may happen, that one is not even able to figure out
by: Fioretti, Guido
Published: (2023)

Ice Cream Doesn't Cause Drowning: Benchmarking LLMs Against Statistical Pitfalls in Causal Inference
by: Du, Jin, et al.
Published: (2025)

Do Math Reasoning LLMs Help Predict the Impact of Public Transit Events?
by: Fang, Bowen, et al.
Published: (2025)

SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions
by: Suvarna, Ashima, et al.
Published: (2026)

Reasoning Models Don't Always Say What They Think
by: Chen, Yanda, et al.
Published: (2025)

When More Data Doesn't Help: Limits of Adaptation in Multitask Learning
by: Hanneke, Steve, et al.
Published: (2026)

Don't Get Too Excited -- Eliciting Emotions in LLMs
by: Fazzi, Gino Franco, et al.
Published: (2025)

Can LLMs Assist Expert Elicitation for Probabilistic Causal Modeling?
by: Shaposhnyk, Olha, et al.
Published: (2025)

Your Instructions Are Not Always Helpful: Assessing the Efficacy of Instruction Fine-tuning for Software Vulnerability Detection
by: Yusuf, Imam Nur Bani, et al.
Published: (2024)

Eliciting Causal Abilities in Large Language Models for Reasoning Tasks
by: Wang, Yajing, et al.
Published: (2024)

Reasoning BO: Enhancing Bayesian Optimization with Long-Context Reasoning Power of LLMs
by: Yang, Zhuo, et al.
Published: (2025)

When Structure Doesn't Help: LLMs Do Not Read Text-Attributed Graphs as Effectively as We Expected
by: Xu, Haotian, et al.
Published: (2025)

Adaptive Generation of Bias-Eliciting Questions for LLMs
by: Staab, Robin, et al.
Published: (2025)