Imagen de Portada

Inference Time Causal Probing in LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Khorasani, Sadegh, Salehkaleybar, Saber, Kiyavash, Negar, Grossglauser, Matthias
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence I.2.6
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Fusing Rewards and Preferences in Reinforcement Learning
por: Khorasani, Sadegh, et al.
Publicado: (2025)

Hierarchical Reinforcement Learning with Targeted Causal Interventions
por: Khorasani, Sadegh, et al.
Publicado: (2025)

Efficiently Escaping Saddle Points for Policy Optimization
por: Khorasani, Sadegh, et al.
Publicado: (2023)

Beyond Mimicry: Preference Coherence in LLMs
por: Mikaelson, Luhan, et al.
Publicado: (2025)

Deep Memory Search: A Metaheuristic Approach for Optimizing Heuristic Search
por: Hedar, Abdel-Rahman, et al.
Publicado: (2024)

Simulation-Based Counterfactual Causal Discovery on Real World Driver Behaviour
por: Howard, Rhys, et al.
Publicado: (2023)

Atomic-Probe Governance for Skill Updates in Compositional Robot Policies
por: Qin, Xue, et al.
Publicado: (2026)

Aligning LLMs on a Budget: Inference-Time Alignment with Heuristic Reward Models
por: Nakamura, Mason, et al.
Publicado: (2025)

Entropy Causal Graphs for Multivariate Time Series Anomaly Detection
por: Febrinanto, Falih Gozi, et al.
Publicado: (2023)

BitCal-TTS: Bit-Calibrated Test-Time Scaling for Quantized Reasoning Models
por: Patarlapalli, Sai Babu, et al.
Publicado: (2026)

Why Online Reinforcement Learning is Causal
por: Schulte, Oliver, et al.
Publicado: (2024)

Causally Grounded Mechanistic Interpretability for LLMs with Faithful Natural-Language Explanations
por: Mahale, Ajay Pravin
Publicado: (2026)

GCAD: Anomaly Detection in Multivariate Time Series from the Perspective of Granger Causality
por: Liu, Zehao, et al.
Publicado: (2025)

Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations
por: Kumar, Sachin
Publicado: (2026)

Multi-Domain Causal Discovery in Bijective Causal Models
por: Jalaldoust, Kasra, et al.
Publicado: (2025)

Evaluating Bivariate Causal Statements Based on Mutual Compatibility
por: Jahn, Erik, et al.
Publicado: (2026)

Integrating Causality with Neurochaos Learning: Proposed Approach and Research Agenda
por: Narendra, Nanjangud C., et al.
Publicado: (2025)

Causal Discovery in Semi-Stationary Time Series
por: Gao, Shanyun, et al.
Publicado: (2024)

CORE: Towards Scalable and Efficient Causal Discovery with Reinforcement Learning
por: Sauter, Andreas W. M., et al.
Publicado: (2024)

Predictive Traffic Rule Compliance using Reinforcement Learning
por: Huang, Yanliang, et al.
Publicado: (2025)

Measuring IIA Violations in Similarity Choices with Bayesian Models
por: Corrêa, Hugo Sales, et al.
Publicado: (2025)

Score-informed Neural Operator for Enhancing Ordering-based Causal Discovery
por: Kang, Jiyeon, et al.
Publicado: (2025)

Teacher-Student Guided Inverse Modeling for Steel Final Hardness Estimation
por: Alsheikh, Ahmad, et al.
Publicado: (2025)

CircuitProbe: Predicting Reasoning Circuits in Transformers via Stability Zone Detection
por: Panuganti, Rajkiran
Publicado: (2026)

Ask WhAI:Probing Belief Formation in Role-Primed LLM Agents
por: Moore, Keith, et al.
Publicado: (2025)

On Semantic Loss Fine-Tuning Approach for Preventing Model Collapse in Causal Reasoning
por: Deshmukh, Pratik, et al.
Publicado: (2026)

Safe Reinforcement Learning with Preference-based Constraint Inference
por: Li, Chenglin, et al.
Publicado: (2026)

The Pragmatic Persona: Discovering LLM Persona through Bridging Inference
por: Yang, Jisoo, et al.
Publicado: (2026)

Collaborative Multi-Agent Scripts Generation for Enhancing Imperfect-Information Reasoning in Murder Mystery Games
por: Zhong, Keyang, et al.
Publicado: (2026)

X-SHIELD: Regularization for eXplainable Artificial Intelligence
por: Sevillano-García, Iván, et al.
Publicado: (2024)

Transformer Mechanisms Mimic Frontostriatal Gating Operations When Trained on Human Working Memory Tasks
por: Traylor, Aaron, et al.
Publicado: (2024)

Comprehensive Metapath-based Heterogeneous Graph Transformer for Gene-Disease Association Prediction
por: Cui, Wentao, et al.
Publicado: (2025)

Scalable and Robust LLM Unlearning by Correcting Responses with Retrieved Exclusions
por: Kim, Junbeom, et al.
Publicado: (2025)

Exploring the Use of ChatGPT for a Systematic Literature Review: a Design-Based Research
por: Huang, Qian, et al.
Publicado: (2024)

AI Benchmark Democratization and Carpentry
por: von Laszewski, Gregor, et al.
Publicado: (2025)

What Do World Models Learn in RL? Probing Latent Representations in Learned Environment Simulators
por: Zhang, Xinyu
Publicado: (2026)

A Self-explainable Model of Long Time Series by Extracting Informative Structured Causal Patterns
por: Wang, Ziqian, et al.
Publicado: (2025)

Causal Discovery-Driven Change Point Detection in Time Series
por: Gao, Shanyun, et al.
Publicado: (2024)

Working Paper: Active Causal Structure Learning with Latent Variables: Towards Learning to Detour in Autonomous Robots
por: Riscos, Pablo de los, et al.
Publicado: (2024)

Unleashing LLMs in Bayesian Optimization: Preference-Guided Framework for Scientific Discovery
por: Yuan, Xinzhe, et al.
Publicado: (2026)