mlsanityData to 14 Oct 2026

EviGraph: Proof-Carrying Selective Recommendation over Temporal Public-Service Knowledge Graphs

arXiv 2610.00212 ↗First posted 21 Sep 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Public-service recommendations require evidence that matches the requested service, scope, and date. Yet treating every missing detail as decisive can withhold useful recommendations. We introduce EviGraph, which distinguishes critical decision requirements from information that can remain unresolved. A language agent links these requirements to evidence in a temporal knowledge graph, while a deterministic checker establishes whether a recommendation is supported. Evaluation on a bilingual Hong Kong public-service benchmark with executable policy references shows that this distinction reduces unnecessary abstention. Additional verification, however, can withdraw supported recommendations without improving decision quality. These findings suggest that reliable evidence-based navigation depends on specifying what must be established for a decision, rather than simply adding more verification.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 20 references that are in the map. First posted on arXiv 21 Sep 2026.

Builds on

14 of 20 references.

References · 14

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  3. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  4. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  5. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  6. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  7. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  8. 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 350
  9. 2020Selective Question Answering under Domain Shiftcited by 238
  10. 2023LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Proverscited by 168
  11. 2024Language Models with Conformal Factuality Guaranteescited by 131
  12. 2025Knowledge Graph-Guided Retrieval Augmented Generationcited by 58
2 more
  1. 2025Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendationcited by 57
  2. 2023Faithful Question Answering with Monte-Carlo Planningcited by 16

Built on by

Not cited yet.