GUARD-IT removes forget-set influence from LLMs via training-free, gated residual-stream rotations at inference, matching gradient unlearning baselines without weight edits.
Title resolution pending
3 Pith papers cite this work, alongside 15 external citations. Polarity classification is still indexing.
3
Pith papers citing it
15
external citations · OpenAlex
citation-role summary
dataset 1
citation-polarity summary
years
2026 3roles
dataset 1polarities
use dataset 1representative citing papers
Synthetically formalizing information needs into topics with descriptions and narratives improves LLM relevance assessor agreement with humans and reduces over-labeling of relevant documents on TREC Deep Learning and Robust04.
LLMs consistently overrate relevance of inadequate passages in IR evaluations due to biases toward length and lexical features rather than true content match.
citing papers explorer
-
Inference-Time Machine Unlearning via Gated Activation Redirection
GUARD-IT removes forget-set influence from LLMs via training-free, gated residual-stream rotations at inference, matching gradient unlearning baselines without weight edits.
-
Formalized Information Needs Improve Large-Language-Model Relevance Judgments
Synthetically formalizing information needs into topics with descriptions and narratives improves LLM relevance assessor agreement with humans and reduces over-labeling of relevant documents on TREC Deep Learning and Robust04.
-
When LLM Judges Inflate Scores: Exploring Overrating in Relevance Assessment
LLMs consistently overrate relevance of inadequate passages in IR evaluations due to biases toward length and lexical features rather than true content match.