STATEWITNESS is a decoder-based activation explainer that audits deception in LLMs by interpreting hidden states, reaching 0.916 mean AUROC on seven datasets with inspectable evidence.
Behonest: Benchmarking honesty in large language models
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 6roles
dataset 1polarities
use dataset 1representative citing papers
RogueAI operationalizes a reverse Turing test as a one-on-two interrogation game to detect licensed deception in LLMs, with pilot data from 467 sessions showing a simple linguistic heuristic at 75.6% accuracy versus 56.6% for human players.
SPADE-Bench is a benchmark that measures spontaneous plan-action divergence in tool-using LLM agents under pressure to distinguish strategic deception from hallucination.
DECOR introduces a theory-grounded multi-agent system that decomposes contexts into atomic units, scores four manipulation dimensions per unit, and aggregates profiles into a global deception index, reporting SOTA results on single- and multi-turn benchmarks.
Toxicity benchmarks for LLMs produce inconsistent results when task type, input domain, or model changes, revealing intrinsic evaluation biases.
Existing LLM unlearning methods fail honesty standards by hallucinating on forgotten knowledge; ReVa improves rejection rates nearly twofold while enhancing retained honesty.
citing papers explorer
-
Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing
STATEWITNESS is a decoder-based activation explainer that audits deception in LLMs by interpreting hidden states, reaching 0.916 mean AUROC on seven datasets with inspectable evidence.
-
RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue
RogueAI operationalizes a reverse Turing test as a one-on-two interrogation game to detect licensed deception in LLMs, with pilot data from 467 sessions showing a simple linguistic heuristic at 75.6% accuracy versus 56.6% for human players.
-
SPADE-Bench: Evaluating Spontaneous Strategic Deception in Agents via Plan-Action Divergence
SPADE-Bench is a benchmark that measures spontaneous plan-action divergence in tool-using LLM agents under pressure to distinguish strategic deception from hallucination.
-
DECOR: Auditing LLM Deception via Information Manipulation Theory
DECOR introduces a theory-grounded multi-agent system that decomposes contexts into atomic units, scores four manipulation dimensions per unit, and aggregates profiles into a global deception index, reporting SOTA results on single- and multi-turn benchmarks.
-
Navigating the Sea of LLM Evaluation: Investigating Bias in Toxicity Benchmarks
Toxicity benchmarks for LLMs produce inconsistent results when task type, input domain, or model changes, revealing intrinsic evaluation biases.
-
Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning
Existing LLM unlearning methods fail honesty standards by hallucinating on forgotten knowledge; ReVa improves rejection rates nearly twofold while enhancing retained honesty.