conftrace_

model internal

10 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (4) representation learning (4) retrieval-augmented generation (2) neural network (1) model introspection (1) answer attribution (1) saliency method (1) knowledge circuit analysis (1) linear probe (1) prompt leakage (1)

Papers

Controllable Context Sensitivity and the Knob Behind It ICLR 2025 Gender Encoding Patterns in Pretrained Language Model Representations NAACL 2025 “I’ve Decided to Leak”: Probing Internals Behind Prompt Leakage Intents EMNLP 2025 NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals ICLR 2025 Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis EMNLP 2025 Do Large Language Models Know How Much They Know? EMNLP 2024 Hypothesis Testing the Circuit Hypothesis in LLMs NeurIPS 2024 Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation EMNLP 2024 Overthinking the Truth: Understanding how Language Models Process False Demonstrations ICLR 2024 Language Models Understand Us, Poorly EMNLP 2022