A text-supervised global layout embedding augments local patch representations in late-interaction VDR, yielding +2.4 nDCG@5 and +2.3 MAP@5 gains over ColPali/ColQwen baselines on ViDoRe-v2.
hub
arXiv preprint arXiv:2508.21038 , year=
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 3
method 1
citation-polarity summary
representative citing papers
Semantic Recall is a new evaluation metric for approximate nearest neighbor search that focuses only on semantically relevant results, with Tolerant Recall as a proxy when relevance labels are unavailable.
LLM-based dense retrievers generalize better when instruction-tuned but pay a specialization tax when optimized for reasoning; they resist typos and corpus poisoning better than encoder-only baselines yet remain vulnerable to semantic perturbations, with larger models and certain embedding geometry,
Embeddings retrieve same-subfield papers at 45-52% but same-agenda papers at only 15-21%; citation rerank reaches 57-59% on agenda queries.
The authors introduce aspect-aware datasets GoldRiM and SilverRiM for math papers and AchGNN, a heterogeneous GNN that outperforms prior methods by jointly modeling textual semantics, citations, and author lineage across aspects.
Neural retrievers that double BM25 performance on QUEST collapse below 0.02 Recall@100 on the new LIMIT+ benchmark while lexical methods reach 0.96, with all methods degrading as compositional depth increases.
Triplet constraints realizable in D-dimensional Euclidean space cannot be preserved above 50% accuracy by any embedding of dimension at most cD for constant c<1, with UGC-hardness preventing better polynomial-time solutions in any dimension.
Generative retrieval beats dense retrieval and BM25 on the LIMIT dataset but degrades with hard negatives due to identifier ambiguity during decoding.
Masked fine-tuning enables autoregressive LLMs to inject new factual knowledge without paraphrases and with reversal-curse resistance, matching diffusion LLM advantages on QA tasks.
MetaEmbed trains fixed learnable Meta Tokens to produce granularity-organized multi-vector embeddings that support test-time scaling in multimodal retrieval.
SIRA compresses multi-round exploratory retrieval into one LLM-guided, corpus-statistic-validated weighted BM25 query and reports superior results over dense retrievers and agentic baselines on BEIR benchmarks.
Argues for a denoising-first paradigm in LLM-oriented information retrieval, framing challenges via a four-stage progression and providing a taxonomy of signal-to-noise optimization techniques across the pipeline.
Foundation models stumble in pathology due to conceptual mismatches with biological tissue, requiring explicitly designed models rather than adaptations of natural-image methods.
citing papers explorer
-
Beyond Bag-of-Patches: Learning Global Layout via Textual Supervision for Late-Interaction Visual Document Retrieval
A text-supervised global layout embedding augments local patch representations in late-interaction VDR, yielding +2.4 nDCG@5 and +2.3 MAP@5 gains over ColPali/ColQwen baselines on ViDoRe-v2.
-
Semantic Recall for Vector Search
Semantic Recall is a new evaluation metric for approximate nearest neighbor search that focuses only on semantically relevant results, with Tolerant Recall as a proxy when relevance labels are unavailable.
-
On the Robustness of LLM-Based Dense Retrievers: A Systematic Analysis of Generalizability and Stability
LLM-based dense retrievers generalize better when instruction-tuned but pay a specialization tax when optimized for reasoning; they resist typos and corpus poisoning better than encoder-only baselines yet remain vulnerable to semantic perturbations, with larger models and certain embedding geometry,
-
Topic Is Not Agenda: A Citation-Community Audit of Text Embeddings
Embeddings retrieve same-subfield papers at 45-52% but same-agenda papers at only 15-21%; citation rerank reaches 57-59% on agenda queries.
-
Aspect-Aware Content-Based Recommendations for Mathematical Research Papers
The authors introduce aspect-aware datasets GoldRiM and SilverRiM for math papers and AchGNN, a heterogeneous GNN that outperforms prior methods by jointly modeling textual semantics, citations, and author lineage across aspects.
-
Reproducing Complex Set-Compositional Information Retrieval
Neural retrievers that double BM25 performance on QUEST collapse below 0.02 Recall@100 on the new LIMIT+ benchmark while lexical methods reach 0.96, with all methods degrading as compositional depth increases.
-
Provable Accuracy Collapse in Embedding-Based Representations under Dimensionality Mismatch
Triplet constraints realizable in D-dimensional Euclidean space cannot be preserved above 50% accuracy by any embedding of dimension at most cD for constant c<1, with UGC-hardness preventing better polynomial-time solutions in any dimension.
-
Generative Retrieval Overcomes Limitations of Dense Retrieval but Struggles with Identifier Ambiguity
Generative retrieval beats dense retrieval and BM25 on the LIMIT dataset but degrades with hard negatives due to identifier ambiguity during decoding.
-
Diffusion-Inspired Masked Fine-Tuning for Knowledge Injection in Autoregressive LLMs
Masked fine-tuning enables autoregressive LLMs to inject new factual knowledge without paraphrases and with reversal-curse resistance, matching diffusion LLM advantages on QA tasks.
-
MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction
MetaEmbed trains fixed learnable Meta Tokens to produce granularity-organized multi-vector embeddings that support test-time scaling in multimodal retrieval.
-
Superintelligent Retrieval Agent: The Next Frontier of Information Retrieval
SIRA compresses multi-round exploratory retrieval into one LLM-guided, corpus-statistic-validated weighted BM25 query and reports superior results over dense retrievers and agentic baselines on BEIR benchmarks.
-
LLM-Oriented Information Retrieval: A Denoising-First Perspective
Argues for a denoising-first paradigm in LLM-oriented information retrieval, framing challenges via a four-stage progression and providing a taxonomy of signal-to-noise optimization techniques across the pipeline.
-
Beyond the Failures: Rethinking Foundation Models in Pathology
Foundation models stumble in pathology due to conceptual mismatches with biological tissue, requiring explicitly designed models rather than adaptations of natural-image methods.