Papersby GlyphRetrieval Augmented Generation Compositionality research paper by IBM, 2026
IBM · Retrieval and data · Oct 21, 2026 · 34 upvotes · unverified
What it shows
This study shows that individual RAG techniques do not always work well together and provides a framework to evaluate full retrieval pipelines.
By Ido Levy, Segev Shlomov, Leshem Choshen · arXiv 2610.29722 · PDF · Code
UnverifiedSummarised by a model from the abstract; not yet checked by hand.
More from IBM
All 5Asking for What Was Never Requested: Horizontal and Vertical Proactivity in AgentsQ&D trains agents to proactively ask for information that is necessary for task completion but not explicitly requested by the user.
IBM41 upvotesRead →Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM AgentsAggregate-score leaderboards in agent benchmarks fail to capture deployment-relevant dimensions and show rank instability, necessitating new evaluation frameworks based on predictive validity and out-of-distribution criteria.IBM2 citations42 upvotesRead →From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM AgentsLLM-based systems use executable workflows that interleave various computational components, with recent approaches organized by workflow structure determination timing and optimization dimensions.IBM34 citations57 upvotesRead →TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP EnvironmentsToucan, a large publicly available tool-agentic dataset, enhances the performance of LLM agents by providing diverse, realistic, and complex multi-tool and multi-turn interactions.IBM69 citations29 upvotesRead →
Other retrieval and data papers
TopicBLOOM: A 176B-Parameter Open-Access Multilingual Language ModelBLOOM, a 176B-parameter open-access language model, achieves competitive performance on various benchmarks and is released publicly with a Responsible AI License.
Hugging Face3,165 citations41 upvotesRead →From Local to Global: A Graph RAG Approach to Query-Focused SummarizationGraphRAG builds a knowledge graph of a document set so a model can answer questions about the whole collection.
Microsoft2,561 citations7 upvotesRead →DINOv3DINOv3, a self-supervised learning model, achieves superior performance across various vision tasks by scaling datasets and models, addressing dense feature degradation, and enhancing flexibility with post-hoc strategies.
Meta1,932 citations320 upvotesRead →Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and RankingThe Qwen3-VL-Embedding and Qwen3-VL-Reranker models form an end-to-end multimodal search pipeline, leveraging multi-stage training and cross-attention mechanisms to achieve high-precision retrieval across diverse modalities.
Alibaba (Qwen)315 citations59 upvotesRead →DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic DataGenerating extensive Lean 4 proof data from mathematical competition problems improved DeepSeekMath 7B's theorem-proving capabilities over GPT-4 and other methods.
DeepSeek284 citations47 upvotesRead →Aya Dataset: An Open-Access Collection for Multilingual Instruction TuningThe initiative builds a human-curated instruction-following dataset spanning 65 languages and creates the largest multilingual collection of instruction-following instances through templating and translating existing datasets across 114 languages, contributing datasets and platforms for participatory research.
Cohere253 citations57 upvotesRead →
About this paper
- Citations
- Not counted yet · Semantic Scholar
- Upvotes
- 34 · Hugging Face
- Lab
- IBM · on Companies · on Acquisitions · on Quarterly · on Paydays · on TechConf
Changes
Hugging Face upvotes fell from 49 to 34.
Hugging Face upvotes fell from 55 to 49.
Hugging Face upvotes rose from 54 to 55.
This study shows that individual RAG techniques do not always work well together and provides a framework to evaluate full retrieval pipelines.
Found by the weekly Hugging Face scan; not yet checked by hand.