A DETR-style probe distills multi-sample claim uncertainty into single-pass span detection and continuous Mixture-of-Beta scores, outperforming baselines on a new 293K-span benchmark.
Natural questions: a benchmark for question answering research
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
The paper proposes Agentic Data Environments that amplify agent capabilities (via information management, retrieval, and elicitation) while bounding failure consequences (via branching and data flow control).
Assigning higher redundancy to semantically important query features reduces retrieval error probability under token erasures, via multivariate Gaussian approximations of similarity margins and supporting numerical results.
Tri-RAG turns external knowledge into Condition-Proof-Conclusion triplets and retrieves via the Condition anchor to improve efficiency and quality in LLM RAG.
CORE is a lightweight two-stage prompt compression method for edge-device RAG QA that builds answer and clue sets via NER and semantic matching then refines them to deliver higher accuracy and lower resource costs than baselines.
citing papers explorer
-
SpanUQ: Span-Level Uncertainty Quantification for Large Language Model Generation
A DETR-style probe distills multi-sample claim uncertainty into single-pass span detection and continuous Mixture-of-Beta scores, outperforming baselines on a new 293K-span benchmark.
-
Agentic Data Environments
The paper proposes Agentic Data Environments that amplify agent capabilities (via information management, retrieval, and elicitation) while bounding failure consequences (via branching and data flow control).
-
Context-Aware Search and Retrieval Under Token Erasure
Assigning higher redundancy to semantically important query features reduces retrieval error probability under token erasures, via multivariate Gaussian approximations of similarity margins and supporting numerical results.
-
Transforming External Knowledge into Triplets for Enhanced Retrieval in RAG of LLMs
Tri-RAG turns external knowledge into Condition-Proof-Conclusion triplets and retrieves via the Condition anchor to improve efficiency and quality in LLM RAG.
-
Less is More: Lightweight Prompt Compression for Question Answering Applications on Edge Devices
CORE is a lightweight two-stage prompt compression method for edge-device RAG QA that builds answer and clue sets via NER and semantic matching then refines them to deliver higher accuracy and lower resource costs than baselines.