Discourse-role labels on identical misleading context cause 56-84 percentage point shifts in LLMs adopting the injected wrong answer.
Sufficient context: A new lens on retrieval augmented generation systems
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
Legal AI benchmarks must evaluate robustness to pro se litigant inputs rather than expert-preprocessed ones to support access-to-justice claims.
A new RAG method that retrieves chunks through aggregated entity descriptions performs on par with or slightly better than plain vector RAG, and both beat Microsoft's GraphRAG on three QA benchmarks.
An LLM framework with RAG predicts query-specific validity horizons for web content expiration and shows gains in production A/B tests.
This research agenda argues that cloud-native architectures, microservices, autoscaling, and emerging trends like serverless inference and federated learning are required to make large language models efficient and scalable.
citing papers explorer
-
Discourse-Role Labels as Presentation-Time Variables for Context Use in Language Models
Discourse-role labels on identical misleading context cause 56-84 percentage point shifts in LLMs adopting the injected wrong answer.
-
Legal Reasoning Is Not Lawyering: Rethinking Legal Benchmarks for Pro Se Access to Justice
Legal AI benchmarks must evaluate robustness to pro se litigant inputs rather than expert-preprocessed ones to support access-to-justice claims.
-
UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough
A new RAG method that retrieves chunks through aggregated entity descriptions performs on par with or slightly better than plain vector RAG, and both beat Microsoft's GraphRAG on three QA benchmarks.
-
RAG-Enhanced Large Language Models for Dynamic Content Expiration Prediction in Web Search
An LLM framework with RAG predicts query-specific validity horizons for web content expiration and shows gains in production A/B tests.
-
Cloud-native and Distributed Systems for Efficient and Scalable Large Language Models -- A Research Agenda
This research agenda argues that cloud-native architectures, microservices, autoscaling, and emerging trends like serverless inference and federated learning are required to make large language models efficient and scalable.