Trajectory Signatures of Deception in Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing interpretability methods exhibit structural limitations in the field of deception detection.
Approach: They propose a method to capture layerwise activations at sparse "decision points" . they capture deception as a dynamic process, a trajectory through the model's hidden-state space .
Outcome: The proposed classifier achieves comparable performance to PCA-reduced probing for binary sycophancy detection and shows preliminary utility for 4-way deception-type classification.

Similar Papers

Truth as a Trajectory: What Internal Representations Reveal About Large Language Model Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Existing explainability methods for Large Language Models treat hidden states as static points in activation space, but they are saturated with polysemantic features.
Approach: They propose a framework that shifts analysis from static activations to layer-wise geometric displacement.
Outcome: The proposed framework outperforms existing explainability methods on commonsense reasoning, question answering, and toxicity detection benchmarks.
LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals (2026.acl-long)

Copied to clipboard

Challenge: Existing models generate tokens by updating high-dimensional representations and decoding from them at each timestep.
Approach: They propose a framework that allows reasoning correction and length control based on derived ideal trajectories.
Outcome: The proposed model can predict correctness and length control based on ideal trajectories.
Hidden in Plain Sight: Evaluation of the Deception Detection Capabilities of LLMs in Multimodal Settings (2025.acl-long)

Copied to clipboard

Challenge: Detecting deception in an increasingly digital world is a critical and challenging task.
Approach: They evaluate the performance of both open-source and proprietary LLMs on three datasets . they find that fine-tuned LLM achieve state-of-the-art performance on textual deception detection .
Outcome: The proposed models achieve state-of-the-art on textual deception detection, whereas LMMs struggle to fully leverage multimodal cues.
GeoLAN: Geometric Learning of Latent Explanatory Directions in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Large language models lack transparency and are often unable to explain causal relationships .
Approach: They propose a training framework that treats token representations as geometric trajectories and applies stickiness conditions to the Kakeya Conjecture.
Outcome: The proposed training framework maintains task accuracy while improving geometric metrics and reducing fairness biases.
Detecting LLM Hallucination Through Layer-wise Information Deficiency: Analysis of Ambiguous Prompts and Unanswerable Questions (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) often generate confident yet inaccurate responses, introducing significant risks for deployment in safety-critical domains.
Approach: They propose a method to detect model hallucination by systematic analysis of information flow across model layers.
Outcome: The proposed approach improves model reliability by immediately integrating with universal LLMs without additional training or architectural modifications.
Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs (2026.acl-long)

Copied to clipboard

Challenge: Current sycophancy research has largely overlooked its specific manifestations in the video-language domain.
Approach: They propose a video-LLM sycophancy benchmarking and evaluation to evaluate scophancies in video-LLMs.
Outcome: The proposed benchmark evaluates sycophantic behavior in state-of-the-art Video-LLMs across diverse question formats, prompt biases, and visual reasoning tasks.
Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) are trained on vast corpora that contain substantial knowledge but their outputs often contain confidently stated inaccuracies.
Approach: They propose to encode truthfulness as a distinct linear feature, termed the "truth direction", which can classify truthfulness reliably.
Outcome: The proposed model can generalize to logical transformations, question-answering tasks, in-context learning, and external knowledge sources.
Where Confabulation Lives: Latent Feature Discovery in LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Despite advances in large language models, hallucination remains a critical failure mode . despite these advances, LLMs are prone to hallucinic outputs that contain illusory information presented as if it were factual or grounded in reality.
Approach: They propose to isolate and analyze confabulation, a foundational aspect of hallucination, where the model fabricates facts about unknown entities.
Outcome: The proposed method reveals that the model can fabricate facts with minimal disruption, shedding light on the inner representations that drive factual and non-factual output.
LLM Beliefs Are in Their Heads (2026.acl-long)

Copied to clipboard

Challenge: Using linear controlled probes, we investigate belief-like representations in decoder-only autoregressive LLMs using residual stream activations and single attention heads.
Approach: They develop four different experiments on decoder-only autoregressive LLMs and examine how they fare against these standards.
Outcome: The proposed representations exhibit strong truth sensitivity and consistent accuracy across models and data sets.
When Truthful Representations Flip Under Deceptive Instructions? (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) follow maliciously crafted instructions to generate deceptive responses, posing safety challenges.
Approach: They use Sparse Autoencoders to analyze LLM's internal representations to determine when and how they "flip" from truthful to deceptive under deceptively crafted instructions.
Outcome: The proposed model's True/False output is predictable across all conditions based on the model''s representation, and the Deceptive instructions induce significant representational shifts compared to Truthful/Neutral representations.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations