PaperMind is a new benchmark that evaluates integrated multimodal reasoning and critique over scientific papers through four complementary task families across seven domains.
Wayne C Booth, Gregory G Colomb, and Joseph M Williams
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
RPC-Bench supplies 15K verified QA pairs and a research-flow taxonomy that shows top foundation models still achieve only 68.2 percent correctness-completeness on academic paper comprehension.
LinkNav creates intra-document connections in academic papers by generating questions from passages via LLM and retrieving answer passages from other parts of the document, with connected passages averaging ten segments apart.
On 190 tasks and a 12-direction cross-modal diagnostic, seven embedding models frequently fail to honor explicit target-modality instructions: retrieval is biased toward the query modality and instruction-induced shifts are misaligned.
citing papers explorer
-
PaperMind: Benchmarking Agentic Reasoning and Critique over Scientific Papers in Multimodal LLMs
PaperMind is a new benchmark that evaluates integrated multimodal reasoning and critique over scientific papers through four complementary task families across seven domains.
-
RPC-Bench: A Fine-grained Benchmark for Research Paper Comprehension
RPC-Bench supplies 15K verified QA pairs and a research-flow taxonomy that shows top foundation models still achieve only 68.2 percent correctness-completeness on academic paper comprehension.
-
LinkNav: Surfacing Interconnected Information in Scientific Articles
LinkNav creates intra-document connections in academic papers by generating questions from passages via LLM and retrieving answer passages from other parts of the document, with connected passages averaging ten segments apart.
-
MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding Models
On 190 tasks and a 12-direction cross-modal diagnostic, seven embedding models frequently fail to honor explicit target-modality instructions: retrieval is biased toward the query modality and instruction-induced shifts are misaligned.