LLM Digest

Story

arxiv_cs_ai · Nov 12, 2026 · paper

Source brief

Cited but Unused: Parametric Provenance in Retrieval-Augmented Generation

arxiv.orgNov 12, 2026
original source linked

In brief

Retrieval-augmented generation systems attach citations to attribute claims to their sources. These citations frequently misstate provenance, and standard verification cannot detect this. We measure provenance by coun...

Feed lens

eval

Read the original at arxiv.org →Open in live feed Read that day’s brief

Cited but Unused: Parametric Provenance in Retrieval-Augmented Generation

Earlier in this thread 4 items

OpticalRAG: Pixel-Space Compression for Token-Efficient Retrieval-Augmented Generation

TRIO: Task Refinement with Individual Optimization for Retrieval-Augmented Generation

Retrieving from Your Own Mistakes: On-Policy Training of Embedding Models for Multi-Hop Retrieval-Augmented Generation

SCoNE: Selective Context-aware Neuron Editing for Robust Retrieval-Augmented Generation