Global calibration metrics like ECE are confounded by accuracy; the proposed ACE framework with three accuracy-controlled views shows many prior calibration advantages weaken or reverse.
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 5roles
dataset 1polarities
use dataset 1representative citing papers
BalanceRAG uses sequential graphical testing on a 2D lattice of threshold pairs to certify safe operating points that meet target risk levels in cascaded RAG while increasing coverage.
SSA uses learned gist tokens to score and selectively unfold relevant context chunks, achieving sparse attention without auxiliary KV caches or architectural changes.
AutoSearch applies RL with a self-answering reward to adaptively determine minimal sufficient search depth in agentic RAG, reducing over-searching while maintaining answer quality on complex questions.
EPGS detects high-confidence factual errors in LLMs by using embedding perturbations to measure gradient sensitivity as a proxy for sharp versus flat minima.
citing papers explorer
-
When Calibration Rankings Reverse: Accuracy-Controlled Evaluation for Fair Comparison of LLMs
Global calibration metrics like ECE are confounded by accuracy; the proposed ACE framework with three accuracy-controlled views shows many prior calibration advantages weaken or reverse.
-
BalanceRAG: Joint Risk Calibration for Cascaded Retrieval-Augmented Generation
BalanceRAG uses sequential graphical testing on a 2D lattice of threshold pairs to certify safe operating points that meet target risk levels in cascaded RAG while increasing coverage.
-
Simplified Sparse Attention via Gist Tokens
SSA uses learned gist tokens to score and selectively unfold relevant context chunks, achieving sparse attention without auxiliary KV caches or architectural changes.
-
AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning
AutoSearch applies RL with a self-answering reward to adaptively determine minimal sufficient search depth in agentic RAG, reducing over-searching while maintaining answer quality on complex questions.
-
From Flat Facts to Sharp Hallucinations: Detecting Stubborn Errors via Gradient Sensitivity
EPGS detects high-confidence factual errors in LLMs by using embedding perturbations to measure gradient sensitivity as a proxy for sharp versus flat minima.