The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Graph-augmented large language models often assume that graph evidence produced by external computation and placed in the input can be used by the native decoder. We test this assumption with HopQA, a...
arXiv:2602. 11745v2 Announce Type: replace Abstract: Graph models are fundamental to data analysis in domains rich with complex relationships.
arXiv:2606. 11562v1 Announce Type: new Abstract: Graph analysis underlies many applications whose answers cannot be looked up in a single record or retrieved along a path: laundering rings, drug repurposing, user preference, and scientific theme are all inferred from a node together with its neighbourhood.
The paper introduces a two-stage diagnostic evaluation to assess the structural reliability of reasoning graphs used in large language models for tasks like multi-hop question answering. Stage 1 examines how graph reliability depends on topology, prompt design, and model family, while Stage 2 evaluates the impact of graph errors on uncertainty estimation. Findings show that graph-based computation is vulnerable to upstream errors, offers limited benefit as prompt context alone, but improves confidence-based answer discrimination and enables node-level diagnostics.
GraphDecisionBench is a benchmark designed to evaluate System One models—such as Jev—that make decisions directly from supplied options on graph-related tasks. The benchmark is model‑independent and incorporates structural task profiles, matched graph‑text input contrasts, and heuristic‑proposal controls to diagnose graph decision performance. Evaluations across fourteen model‑interface configurations reveal that accurate adjacency recognition does not guarantee broader structural correctness, joint graph‑text input does not consistently improve prediction, and feasible construction does not ensure high solution quality.
ThreadRAG is a retrieval‑augmented generation framework that preserves contextual consistency by structuring retrieved documents into Semantic Nodes and building a Semantic Topology Graph (STG). It uses Energy‑Driven Pathfinding (EDP) to identify query‑relevant subgraphs and linearize them into coherent textual evidence paths. Experiments on HotpotQA, 2WikiMultihop, and another benchmark show ThreadRAG outperforms strong baselines, achieving a 14.4% EM gain on HotpotQA and a 5.8% EM lead on 2WikiMultihop while cutting token cost to 23.3% of the strongest baseline.