REVIEW 8 cited by
Do LLMs Know about Hallucination? An Empirical Investigation of LLM's Hidden States
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Large Language Models (LLMs) can make up answers that are not real, and this is known as hallucination. This research aims to see if, how, and to what extent LLMs are aware of hallucination. More specifically, we check whether and how an LLM reacts differently in its hidden states when it answers a question right versus when it hallucinates. To do this, we introduce an experimental framework which allows examining LLM's hidden states in different hallucination situations. Building upon this framework, we conduct a series of experiments with language models in the LLaMA family (Touvron et al., 2023). Our empirical findings suggest that LLMs react differently when processing a genuine response versus a fabricated one. We then apply various model interpretation techniques to help understand and explain the findings better. Moreover, informed by the empirical observations, we show great potential of using the guidance derived from LLM's hidden representation space to mitigate hallucination. We believe this work provides insights into how LLMs produce hallucinated answers and how to make them occur less often.
Forward citations
Cited by 8 Pith papers
-
Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations
SSP adds a learned, sample-specific noise prompt to an LLM input and scores hallucination by the cosine shift in intermediate representations, outperforming output-confidence baselines on QA benchmarks.
-
Entropy Sentinel: Probing Entropy Traces for LLM Monitoring
Top-k decoding-entropy profiles can estimate and rank held-out domain accuracy for most tested LLMs, with difficulty-diverse training data the main success factor.
-
ExploreGS: Explorable 3D Scene Reconstruction with Virtual Camera Samplings and Diffusion Priors
Adding information-gain-selected virtual views refined by video diffusion priors to 3D Gaussian Splatting improves arbitrary-view rendering quality.
-
CoRE: Enhancing Metacognition with Label-free Self-evaluation in LRMs
A training-free and label-free detector of cyclic hidden-state patterns triggers early exit during chain-of-thought reasoning, reducing token length while mostly preserving or improving accuracy.
-
LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMs
Linear probe accuracy on simple code metrics can guide layer pruning and roughly predict post-fine-tuning vulnerability detection performance, but several headline numbers in the abstract do not match the paper's own tables.
-
Shadows in the Attention: Contextual Perturbation and Representation Drift in the Dynamics of Hallucination in LLMs
Context injection shifts LLM hidden states and attention, and the paper claims this drift tracks and eventually "locks in" hallucination behavior, but the reported data contain internal inconsistencies.
-
Toward Better Generalisation in Uncertainty Estimators: Leveraging Data-Agnostic Features
Adding data-agnostic probability and entropy features to hidden-state probes improves cross-task generalization in most but not all evaluated transfer pairs.
-
From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models
The paper argues hallucinations and jailbreaks share the same optimization dynamics and shows that defenses for one also reduce the other, but the theoretical support is largely circular.
Discussion (0). Sign in to comment.