ChartWalker provides a hierarchical knowledge graph construction method and structure-aware sampling to generate cross-chart RAG benchmarks, releasing ChartWalker-Bench that exposes performance gaps across RAG paradigms.
Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 7roles
background 2representative citing papers
Multimodal LLMs process code as images to achieve up to 8x token compression, with visual cues like syntax highlighting aiding tasks and clone detection remaining resilient or even improving under compression.
SLMs solve multi-hop QA by first producing a quick answer and then retrieving evidence based on that hypothesis for System-II reasoning, outperforming think-first baselines.
LLM reasoning is primarily mediated by latent-state trajectories rather than by explicit surface chain-of-thought outputs.
Hybrid Document-Routed Retrieval (HDRR) filters financial filings with LLM document routing then scopes chunk retrieval, beating pure chunk and pure file routing on FinDER accuracy and efficiency.
Sol2Vy transfers vulnerability detection from Solidity to Vyper in zero-shot fashion, outperforming prior methods on reentrancy, weak randomness, and unchecked transfers.
Neural reranking in a hybrid RAG system raises high-quality answer rates from 33.5% to 49.0% on financial report questions.
citing papers explorer
-
ChartWalker: Benchmarking the Cross-Chart RAG Task with Hierarchical Knowledge Graphs
ChartWalker provides a hierarchical knowledge graph construction method and structure-aware sampling to generate cross-chart RAG benchmarks, releasing ChartWalker-Bench that exposes performance gaps across RAG paradigms.
-
CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding
Multimodal LLMs process code as images to achieve up to 8x token compression, with visual cues like syntax highlighting aiding tasks and clone detection remaining resilient or even improving under compression.
-
Can Hallucinations Be Useful? Solving Multi-Hop Questions With SLMs By Chaining System-I/II Reasoning
SLMs solve multi-hop QA by first producing a quick answer and then retrieving evidence based on that hypothesis for System-II reasoning, outperforming think-first baselines.
-
LLM Reasoning Is Latent, Not the Chain of Thought
LLM reasoning is primarily mediated by latent-state trajectories rather than by explicit surface chain-of-thought outputs.
-
Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-off
Hybrid Document-Routed Retrieval (HDRR) filters financial filings with LLM document routing then scopes chunk retrieval, beating pure chunk and pure file routing on FinDER accuracy and efficiency.
-
Zero-Shot Vulnerability Detection in Low-Resource Smart Contracts Through Solidity-Only Training
Sol2Vy transfers vulnerability detection from Solidity to Vyper in zero-shot fashion, outperforming prior methods on reentrancy, weak randomness, and unchecked transfers.
-
Enhancing Financial Report Question-Answering: A Retrieval-Augmented Generation System with Reranking Analysis
Neural reranking in a hybrid RAG system raises high-quality answer rates from 33.5% to 49.0% on financial report questions.