Image de couverture de livre

Interpreting Learned Feedback Patterns in Large Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Marks, Luke, Abdullah, Amir, Neo, Clement, Arike, Rauno, Krueger, David, Torr, Philip, Barez, Fazl
Format:	Preprint
Publié:	2023
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Towards Interpreting Visual Information Processing in Vision-Language Models
par: Neo, Clement, et autres
Publié: (2024)

Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders
par: Marks, Luke, et autres
Publié: (2024)

Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models
par: Lan, Michael, et autres
Publié: (2023)

Understanding Addition and Subtraction in Transformers
par: Quirke, Philip, et autres
Publié: (2024)

Interpreting Context Look-ups in Transformers: Investigating Attention-MLP Interactions
par: Neo, Clement, et autres
Publié: (2024)

Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders
par: Lan, Michael, et autres
Publié: (2024)

Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
par: Oozeer, Narmeen, et autres
Publié: (2025)

TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Research
par: Harrasse, Abir, et autres
Publié: (2025)

Beyond Linear Probes: Dynamic Safety Monitoring for Language Models
par: Oldfield, James, et autres
Publié: (2025)

Do Sparse Autoencoders Generalize? A Case Study of Answerability
par: Heindrich, Lovis, et autres
Publié: (2025)

Technical Report: Evaluating Goal Drift in Language Model Agents
par: Arike, Rauno, et autres
Publié: (2025)

Understanding Addition in Transformers
par: Quirke, Philip, et autres
Publié: (2023)

Rethinking Safety in LLM Fine-tuning: An Optimization Perspective
par: Kim, Minseon, et autres
Publié: (2025)

SafetyNet: Detecting Harmful Outputs in LLMs by Modeling and Monitoring Deceptive Behaviors
par: Chaudhary, Maheep, et autres
Publié: (2025)

Same Question, Different Words: A Latent Adversarial Framework for Prompt Robustness
par: Fu, Tingchen, et autres
Publié: (2025)

PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning
par: Fu, Tingchen, et autres
Publié: (2024)

C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning
par: Mittal, Avni, et autres
Publié: (2026)

Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer
par: Schrodi, Simon, et autres
Publié: (2025)

Visualizing Neural Network Imagination
par: Wichers, Nevan, et autres
Publié: (2024)

Scaling sparse feature circuit finding for in-context learning
par: Kharlapenko, Dmitrii, et autres
Publié: (2025)

Large Language Models Relearn Removed Concepts
par: Lo, Michelle, et autres
Publié: (2024)

Informal Safety Guarantees for Simulated Optimizers Through Extrapolation from Partial Simulations
par: Marks, Luke
Publié: (2023)

Interpreting Emergent Planning in Model-Free Reinforcement Learning
par: Bush, Thomas, et autres
Publié: (2025)

Open Problems in Machine Unlearning for AI Safety
par: Barez, Fazl, et autres
Publié: (2025)

Query Circuits: Explaining How Language Models Answer User Prompts
par: Wu, Tung-Yu, et autres
Publié: (2025)

Beyond Monoliths: Expert Orchestration for More Capable, Democratic, and Safe Language Models
par: Quirke, Philip, et autres
Publié: (2025)

Interpretability Can Be Actionable
par: Orgad, Hadas, et autres
Publié: (2026)

Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
par: Yang, Puning, et autres
Publié: (2026)

Taxonomy, Opportunities, and Challenges of Representation Engineering for Large Language Models
par: Wehner, Jan, et autres
Publié: (2025)

An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models
par: Pan, Yangchen, et autres
Publié: (2024)

Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
par: Karvonen, Adam, et autres
Publié: (2024)

Revisiting Uncertainty Estimation and Calibration of Large Language Models
par: Tao, Linwei, et autres
Publié: (2025)

Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models
par: Eiras, Francisco, et autres
Publié: (2024)

VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models
par: Han, Junlin, et autres
Publié: (2024)

Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation
par: Yang, Yibo, et autres
Publié: (2024)

TraceDet: Hallucination Detection from the Decoding Trace of Diffusion Large Language Models
par: Chang, Shenxu, et autres
Publié: (2025)

Understanding Reasoning in Thinking Language Models via Steering Vectors
par: Venhoff, Constantin, et autres
Publié: (2025)

Improving Adversarial Transferability via Model Alignment
par: Ma, Avery, et autres
Publié: (2023)

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
par: Marks, Samuel, et autres
Publié: (2024)

Base Models Know How to Reason, Thinking Models Learn When
par: Venhoff, Constantin, et autres
Publié: (2025)