Live intelligence

Latest AI updates

4 updates
Research

Benchmarking LLMs on Heterogeneous Cognitive and Biomedical Knowledge Graphs

The study benchmarks GPT-5.1, Gemini 2.0 Pro, Llama 3, Qwen, and BioGPT across DrugBank, NeuroSynth, Cognitive Atlas, Brain Map, and GDPKG using a multitier query dataset under graph-grounded and graph-agnostic conditions. It reports that general-purpose models generally outperform domain-specific models on multi-hop and high-level reasoning, although performance declines as query complexity increases. Knowledge-graph grounding reduces hallucination rates across all evaluated models, while domain-specific models do not consistently outperform general-purpose models on specialized tasks without grounding.

Large language modelsKnowledge graphsBiomedical AI
Research Editor selected

SciGraphSelect: Auditable Scientific Data Selection through Knowledge--Reasoning Graphs

SciGraphSelect is a framework that uses typed knowledge-reasoning graphs to score scientific documents based on concept coverage, relational co-support, and directional alignment. It preserves rich relational structure on the reference side while treating candidate evidence conservatively to avoid over-interpreting embeddings. The method provides traceability for constructing scientific training corpora and complements downstream verification tasks.

Why it matters: Introduces a novel, auditable approach to scientific data selection that enhances transparency and traceability in AI training corpus construction.

scientific data selectionknowledge graphsAI training corpora
Research

FIRME: Registry-Anchored Memory Graphs for Evolving, Heterogeneous Investor Knowledge

FIRME is a registry-anchored memory graph designed to reconcile recurring investor observations into persistent canonical relationships while retaining source, time, and context. It uses rule-based within-period fusion to link investor-call discussions with portfolio cash-flow signals, and cross-period alias memory to direct recurring observations to the same relationship history. Evaluated on proprietary investor-call and cash-flow records and S&P 500 earnings-call transcripts, FIRME improved final-period Correct Match Rate by 7.8–12.1 percentage points over a registry without alias memory across four settings. A blinded human audit also reported higher Correct Match Rate and reattachment recall, and a separate audit found valid evidence paths for 293 of 300 outputs in the investor-call setting.

AI memoryknowledge graphsfinancial AI
Research

FoG: Training KG Agents to Retrieve the Evidence Behind Their Answers

FoG is a framework for training knowledge-graph agents to retrieve the supporting triples behind factual answers, not merely produce correct answers. It combines evidence-grounded synthesis that hides explicit entities behind verifiable sub-questions, a KG interaction agent that records returned triples, and an evidence-coverage process reward that credits each supporting triple to the turn that first retrieves it. Experiments on three KGQA benchmarks show 3B–4B open-source agents outperforming substantially larger baselines in answer accuracy and evidence coverage, with zero-shot cross-KG transfer.

knowledge graphsLLM agentsevidence retrieval