Atropos uses GCN on inference graphs for early failure prediction and hotswaps to larger LLMs, achieving 74% of large-model performance at 24% cost.
InFindings of the Association for Computational Linguistics: ACL 2024, Lun-Wei Ku, Andre Martins, and Vivek Srikumar (Eds.)
6 Pith papers cite this work, alongside 7 external citations. Polarity classification is still indexing.
6
Pith papers citing it
7
external citations · OpenAlex
representative citing papers
LaaB improves LLM hallucination detection by mapping self-judgment labels back into neural feature space and using mutual learning under logical consistency constraints between responses and meta-judgments.
Clotho ranks LLM test inputs by failure likelihood using a Gaussian mixture model over pre-generation hidden states of passing inputs, reaching 0.716 ROC-AUC with 5.4% labelling and transferring from open-weight to proprietary LLMs.
Adapts multi-layer token-level Mahalanobis distance with supervised linear regression to yield improved uncertainty scores for LLM truthfulness tasks.
A factorized study finds raw hidden states and attention features hard to beat in-domain for LLM uncertainty probes, but structured compressed features are more robust under distribution shift, with pretrained probes transferring to open-ended generation.
SIVR detects LLM hallucinations by learning from token-wise and layer-wise variance patterns in internal hidden states, outperforming baselines with better generalization and less training data.
citing papers explorer
-
Atropos: Improving Cost-Benefit Trade-off of LLM-based Agents under Self-Consistency with Early Termination and Model Hotswap
Atropos uses GCN on inference graphs for early failure prediction and hotswaps to larger LLMs, achieving 74% of large-model performance at 24% cost.
-
Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments
LaaB improves LLM hallucination detection by mapping self-judgment labels back into neural feature space and using mutual learning under logical consistency constraints between responses and meta-judgments.
-
Clotho: Measuring Task-Specific Pre-Generation Test Adequacy for LLM Inputs
Clotho ranks LLM test inputs by failure likelihood using a Gaussian mixture model over pre-generation hidden states of passing inputs, reaching 0.716 ROC-AUC with 5.4% labelling and transferring from open-weight to proprietary LLMs.
-
Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models
Adapts multi-layer token-level Mahalanobis distance with supervised linear regression to yield improved uncertainty scores for LLM truthfulness tasks.
-
From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models
A factorized study finds raw hidden states and attention features hard to beat in-domain for LLM uncertainty probes, but structured compressed features are more robust under distribution shift, with pretrained probes transferring to open-ended generation.
-
Learning Uncertainty from Sequential Internal Dispersion in Large Language Models
SIVR detects LLM hallucinations by learning from token-wise and layer-wise variance patterns in internal hidden states, outperforming baselines with better generalization and less training data.