FORGE benchmark shows domain-specific knowledge, not visual grounding, is the main bottleneck for MLLMs in manufacturing, with SFT on a 3B model delivering up to 90.8% relative accuracy improvement on held-out scenarios.
Graphomni: A comprehensive and extendable benchmark framework for large language models on graph-theoretic tasks
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
background 1representative citing papers
RankFlow deploys four LLM roles in sequence to rewrite queries, generate pseudo-answers, summarize passages, and rerank candidates, outperforming prior methods on TREC-DL, BEIR, and NovelEval.
EGL-SCA co-evolves instructions and tools via structural credit assignment in graph reasoning agents and reports 92% average success on four benchmarks.
A survey of LLMs for graph computation introduces a role-based taxonomy of executors versus planners and concludes that current models suit simple small-scale tasks but remain unreliable for large-scale exact computation.
citing papers explorer
-
RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models
RankFlow deploys four LLM roles in sequence to rewrite queries, generate pseudo-answers, summarize passages, and rerank candidates, outperforming prior methods on TREC-DL, BEIR, and NovelEval.
-
EGL-SCA: Structural Credit Assignment for Co-Evolving Instructions and Tools in Graph Reasoning Agents
EGL-SCA co-evolves instructions and tools via structural credit assignment in graph reasoning agents and reports 92% average success on four benchmarks.
-
Are Large Language Models Suitable for Graph Computation? Progress and Prospects
A survey of LLMs for graph computation introduces a role-based taxonomy of executors versus planners and concludes that current models suit simple small-scale tasks but remain unreliable for large-scale exact computation.