Chain of Evidence introduces a retriever-agnostic visual attribution method for iRAG that reasons over document screenshots with VLMs to output precise bounding boxes, outperforming text baselines on Wiki-CoE and SlideVQA.
Title resolution pending
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Generative AI enables scalable, context-aware spear phishing by extracting profiles from public social media, producing emails that outperform real-world phishing samples in personalization and lower recipient suspicion.
HTDC mitigates hallucinations in LVLMs by triggering calibration only at hesitation-prone decoding steps via contrasts with visual-nullification and semantic-nullification probes.
LGCD creates pseudo-overlapping user data via LLM reasoning and uses conditional diffusion to generate target-domain user representations for inter-domain sequential recommendation without real overlapping users.
CiteAudit supplies a human-validated benchmark and multi-agent verification system that outperforms existing LLMs and commercial tools at detecting hallucinated scientific references.
A retrieval-augmented SLM uses FCA to verify implications in growing formal contexts, reporting relation F1 0.29-0.52 and implication F1 0.22-0.30 on a rare ataxia ontology task.
A3D is an agentic AI system that automates end-to-end hardware accelerator design for complex applications like LAMMPS and QMCPACK with no human intervention.
Mujica-MyGo decomposes multi-turn RAG interactions via multi-agent workflows and applies minimalist policy gradient optimization to improve performance on QA benchmarks while avoiding long-context problems.
A review of 38 studies finds LLMs mostly target text-based accessibility tasks under WCAG guidelines, with limited attention to cognitive issues and rare direct involvement of disabled users in evaluations.
citing papers explorer
-
Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation
Chain of Evidence introduces a retriever-agnostic visual attribution method for iRAG that reasons over document screenshots with VLMs to output precise bounding boxes, outperforming text baselines on Wiki-CoE and SlideVQA.
-
HTDC: Hesitation-Triggered Differential Calibration for Mitigating Hallucination in Large Vision-Language Models
HTDC mitigates hallucinations in LVLMs by triggering calibration only at hesitation-prone decoding steps via contrasts with visual-nullification and semantic-nullification probes.
-
From Clues to Generation: Language-Guided Conditional Diffusion for Cross-Domain Recommendation
LGCD creates pseudo-overlapping user data via LLM reasoning and uses conditional diffusion to generate target-domain user representations for inter-domain sequential recommendation without real overlapping users.
-
CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era
CiteAudit supplies a human-validated benchmark and multi-agent verification system that outperforms existing LLMs and commercial tools at detecting hallucinated scientific references.
-
Verifiable Knowledge Expansion through Retrieval-Grounded Formal Concept Analysis
A retrieval-augmented SLM uses FCA to verify implications in growing formal contexts, reporting relation F1 0.29-0.52 and implication F1 0.22-0.30 on a rare ataxia ontology task.
-
A3D: Agentic AI flow for autonomous Accelerator Design
A3D is an agentic AI system that automates end-to-end hardware accelerator design for complex applications like LAMMPS and QMCPACK with no human intervention.
-
Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning
Mujica-MyGo decomposes multi-turn RAG interactions via multi-agent workflows and applies minimalist policy gradient optimization to improve performance on QA benchmarks while avoiding long-context problems.