Image de couverture de livre

LogProber: Disentangling confidence from contamination in LLM responses

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yax, Nicolas, Oudeyer, Pierre-Yves, Palminteri, Stefano
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

PhyloLM : Inferring the Phylogeny of Large Language Models and Predicting their Performances in Benchmarks
par: Yax, Nicolas, et autres
Publié: (2024)

Relative Value Biases in Large Language Models
par: Hayes, William M., et autres
Publié: (2024)

Large Language Models are Biased Reinforcement Learners
par: Hayes, William M., et autres
Publié: (2024)

Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI
par: Pourcel, Julien, et autres
Publié: (2025)

Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning
par: Zou, Jiaru, et autres
Publié: (2025)

Stick to your Role! Stability of Personal Values Expressed in Large Language Models
par: Kovač, Grgur, et autres
Publié: (2024)

Recursive Training Loops in LLMs: How training data properties modulate distribution shift in generated data?
par: Kovač, Grgur, et autres
Publié: (2025)

Automatic Generation of Question Hints for Mathematics Problems using Large Language Models in Educational Technology
par: Tonga, Junior Cedric, et autres
Publié: (2024)

WorldLLM: Improving LLMs' world modeling using curiosity-driven theory-making
par: Levy, Guillaume, et autres
Publié: (2025)

LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation
par: Chen, Han, et autres
Publié: (2025)

Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey
par: Colas, Cédric, et autres
Publié: (2020)

SAC-GLAM: Improving Online RL for LLM agents with Soft Actor-Critic and Hindsight Relabeling
par: Gaven, Loris, et autres
Publié: (2024)

Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
par: Boppana, Siddharth, et autres
Publié: (2026)

Log-Likelihood, Simpson's Paradox, and the Detection of Machine-Generated Text
par: Kempton, Tom, et autres
Publié: (2026)

From Chat Logs to Collective Insights: Aggregative Question Answering
par: Zhang, Wentao, et autres
Publié: (2025)

ODIN: Disentangled Reward Mitigates Hacking in RLHF
par: Chen, Lichang, et autres
Publié: (2024)

Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation
par: Chen, Peter Baile, et autres
Publié: (2025)

Anonymous-by-Construction: An LLM-Driven Framework for Privacy-Preserving Text
par: Albanese, Federico, et autres
Publié: (2026)

Latent Concept Disentanglement in Transformer-based Language Models
par: Hong, Guan Zhe, et autres
Publié: (2025)

Quantifying Modality Contributions via Disentangling Multimodal Representations
par: Amit, Padegal, et autres
Publié: (2025)

Disentangling Exploration of Large Language Models by Optimal Exploitation
par: Grams, Tim, et autres
Publié: (2025)

Evaluating the Relevance of Uncertainty Estimators for LLM Hallucination
par: Agnimo, Yedidia, et autres
Publié: (2026)

Subliminal Effects in Your Data: A General Mechanism via Log-Linearity
par: Aden-Ali, Ishaq, et autres
Publié: (2026)

Interpretable Discriminative Text Representations via Agreement and Label Disentanglement
par: Wang, Tong, et autres
Publié: (2026)

Disentangling the Roles of Target-Side Transfer and Regularization in Multilingual Machine Translation
par: Meng, Yan, et autres
Publié: (2024)

Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities
par: Hua, Wenyue, et autres
Publié: (2024)

EuroLLM-9B: Technical Report
par: Martins, Pedro Henrique, et autres
Publié: (2025)

ACES: Generating Diverse Programming Puzzles with with Autotelic Generative Models
par: Pourcel, Julien, et autres
Publié: (2023)

EuroLLM-22B: Technical Report
par: Ramos, Miguel Moura, et autres
Publié: (2026)

Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment
par: Krishna, Kundan, et autres
Publié: (2025)

Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement
par: Islam, Sekh Mainul, et autres
Publié: (2025)

Disentangling Task Conflicts in Multi-Task LoRA via Orthogonal Gradient Projection
par: Yang, Ziyu, et autres
Publié: (2026)

Disentangling Feature Structure: A Mathematically Provable Two-Stage Training Dynamics in Transformers
par: Gong, Zixuan, et autres
Publié: (2025)

From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?
par: Mueller, Aaron, et autres
Publié: (2025)

Detecting Relevant Information in High-Volume Chat Logs: Keyphrase Extraction for Grooming and Drug Dealing Forensic Analysis
par: Alves, Jeovane Honório, et autres
Publié: (2023)

Towards Multilingual LLM Evaluation for European Languages
par: Thellmann, Klaudia, et autres
Publié: (2024)

DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis
par: Wang, Pan, et autres
Publié: (2024)

Improved Performances and Motivation in Intelligent Tutoring Systems: Combining Machine Learning and Learner Choice
par: Clément, Benjamin, et autres
Publié: (2024)

Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-Preferences
par: Karlekar, Sweta, et autres
Publié: (2026)

The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems
par: Ren, Richard, et autres
Publié: (2025)