conftrace_

internal state analysis

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

hallucination detection (3) large language model (2) consistency checking (2) retrieval-augmented generation (2) white-box setting (1) black-box setting (1) hidden state analysis (1) training data (1) attention map (1) calibration error (1)

Papers

ISACL: Internal State Analyzer for Copyrighted Training Data Leakage EMNLP 2025 Visualizing and Benchmarking LLM Factual Hallucination Tendencies via Internal State Analysis and Clustering IJCNLP 2025 InternalInspector I2: Robust Confidence Estimation in LLMs through Internal States EMNLP 2024 LLM-Check: Investigating Detection of Hallucinations in Large Language Models NeurIPS 2024 Transferable and Efficient Non-Factual Content Detection via Probe Training with Offline Consistency Checking ACL 2024