No article text was recorded for this version.
internal state probing
Version 1 of 195 papers122 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Efficient Contrastive Decoding with Probabilistic Hallucination Detection - Mitigating Hallucinations in Large Vision Language Models -
- Blog: The Internal State of an LLM Knows When its Lying
- Blog: Enhancing Fact Retrieval in PLMs through Truthfulness
- Blog: HALLUCANA: Fixing LLM Hallucination with A Canary Lookahead
- Blog: The Internal State of an LLM Knows When It's Lying
- Blog: Enhancing Fact Retrieval in PLMs through Truthfulness
- Blog: Knowledge Boundary of Large Language Models: A Survey
- Blog: LLM Factoscope: Uncovering LLMs' Factual Discernment through Inner States Analysis
- Blog: Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contexts
- Blog: Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models
- Blog: Towards Improving Open-box Hallucination Detection in Large Language Models (LLMs)
- Blog: Prompt-Guided Internal States for Hallucination Detection of Large Language Models
- Blog: HausaNLP at SemEval-2025 Task 3: Towards a Fine-Grained Model-Aware Hallucination Detection
- Blog: Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contexts
- Blog: Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification
- Blog: Do Androids Know They're Only Dreaming of Electric Sheep?
- Blog: Do Transformer Interpretability Methods Transfer to RNNs?
- Blog: Unsupervised Hallucination Detection by Inspecting Reasoning Processes
- Blog: Are the Hidden States Hiding Something? Testing the Limits of Factuality-Encoding Capabilities in LLMs
- Blog: Estimating Knowledge in Large Language Models Without Generating a Single Token
- Blog: NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models
- Blog: HalluEntity: Benchmarking and Understanding Entity-Level Hallucination Detection
- Blog: Emergence of Linear Truth Encodings in Language Models
- Blog: On the Universal Truthfulness Hyperplane Inside LLMs
- Blog: Personas as a Way to Model Truthfulness in Language Models
- Blog: Simple Factuality Probes Detect Hallucinations in Long-Form Natural Language Generation
- Blog: Is This Just Fantasy? Language Model Representations Reflect Human Judgments of Event Plausibility
- Blog: Reference-free Hallucination Detection for Large Vision-Language Models
- Blog: Knowledge-Centric Hallucination Detection
- Blog: What LLMs Explain Is Not What They Believe: Evaluating Explanation Sufficiency Under Models' Own Input Beliefs
- Blog: A Survey on the Honesty of Large Language Models
- Blog: HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection
- Blog: Unified Active Retrieval for Retrieval Augmented Generation
- Blog: Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models
- Blog: A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia
- Blog: Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before Completion
- Blog: Unsupervised Token-level Hallucination Detection from Summary Generation By-products
- Blog: Real-Time Detection of Hallucinated Entities in Long-Form Generation
- Blog: Attributive Reasoning for Hallucination Diagnosis of Large Language Models
- Blog: Discovering Latent Knowledge in Language Models Without Supervision
- Blog: Reference-free Hallucination Detection for Large Vision-Language Models
- Blog: Bold Claims or Self-Doubt? Factuality Hallucination Type Detection via Belief State
- Blog: Do Androids Know They're Only Dreaming of Electric Sheep?
- Blog: LLM-Check: Investigating Detection of Hallucinations in Large Language Models
- Blog: NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models
- Blog: A Survey of Language Model Confidence Estimation and Calibration
- Blog: Lightweight Latent Verifiers for Efficient Meta-Generation Strategies
- Blog: Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits
- Blog: Harnessing Reasoning Trajectories for Hallucination Detection via Answer-agreement Representation Shaping
- Blog: Can VLMs Recall Factual Associations From Visual References?
- Blog: Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding
- Blog: Detecting Hallucination in Large Language Models Through Deep Internal Representation Analysis
- Blog: Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment
- Blog: Prompt-Guided Internal States for Hallucination Detection of Large Language Models
- Blog: SemEval-2024 Task 6: SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes
- Blog: MetaToken: Detecting Hallucination in Image Descriptions by Meta Classification
- Blog: Representation Engineering: A Top-Down Approach to AI Transparency
- Blog: When Truthful Representations Flip Under Deceptive Instructions?
- Blog: Automatic Layer Selection for Hallucination Detection
- Blog: Evaluating the Factuality of Large Language Models using Large-Scale Knowledge Graphs
Showing 60 of 95 papers.
History & citation
Current · Permanent link
- The Internal Geometry of Truth in Language Models merged into this direction (59% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_internal_state_probing_2160be43,
title = {internal state probing},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/internal-state-probing/rdr_2160be438cd7428d8669082fcdfdcf52},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_internal_state_probing_2160be43_v1,
title = {internal state probing},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/internal-state-probing/rdr_2160be438cd7428d8669082fcdfdcf52/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}