EgoMemReason is a new benchmark showing that even the best multimodal models achieve only 39.6% accuracy on reasoning tasks that require integrating sparse evidence across days in egocentric video.
Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: Long papers) , pages=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Multilingual LLMs show a reproducible 'Illusion of Cultural Alignment': they can be fluent in a language while lacking the culture's factual knowledge, and confidence, sampling, and retrieval do not fix it.
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.
citing papers explorer
-
EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding
EgoMemReason is a new benchmark showing that even the best multimodal models achieve only 39.6% accuracy on reasoning tasks that require integrating sparse evidence across days in egocentric video.
-
MSQA: A Natively Sourced Multilingual and Multicultural SimpleQA Benchmark
Multilingual LLMs show a reproducible 'Illusion of Cultural Alignment': they can be fluent in a language while lacking the culture's factual knowledge, and confidence, sampling, and retrieval do not fix it.
-
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.