Starting with a local Parquet file, then joining it to data stored in the cloud The post Building a Data Lakehouse with DuckDB and DuckLake appeared first on Towards Data Science.
arXiv:2606. 23697v1 Announce Type: cross Abstract: Semantic segmentation of code written in a C-family language remains a challenging problem, due to the language's complex syntax, macro expansion, and irregular structural patterns.
The paper introduces a configurable semantic chunking framework for biomedical information extraction in retrieval‑augmented generation systems. It replaces the fixed‑size chunking stage of BioMedRAG with entity‑preserving windows, trigger‑centered chunking, proposition‑first extraction, tiered trigger prioritization, and hierarchical relation resolution, while keeping the rest of the pipeline unchanged. Experiments on relation extraction benchmarks (GM‑CIHT, DDI, ChemProt) and adverse event classification (ADE) show that the hybrid configuration boosts performance on datasets with explicit relation cues, achieving 82.6% F1 on GM‑CIHT compared to 74.2% with the baseline.
The paper evaluates how different chunking strategies—fixed-size, recursive paragraph-first, and content-defined—affect the cost of updating embeddings when Wikipedia documents are revised. Using 120 pairs of Chinese and English revisions, the authors find that fixed-size chunking requires the most recomputation (57‑68 % of the workload), while recursive and content-defined chunking need less (38‑56 % and 43‑54 % respectively). Despite these differences, evidence recall under a 2048‑token retrieval budget varies by less than two percentage points across methods and languages.
arXiv:2603. 29875v3 Announce Type: replace-cross Abstract: One of the key problems in Retrieval-augmented generation (RAG) systems is that chunk-based retrieval pipelines represent the source chunks as atomic objects, mixing the information contained within such a chunk into a single vector.
arXiv:2606. 13141v1 Announce Type: new Abstract: Retrieval-augmented generation is moving beyond text into long, egocentric video, where systems must select query-relevant chunks across multiple modalities and temporal granularities.
Retrieval-augmented generation (RAG) improves large language model (LLM) answer quality by grounding generation in external evidence, but processing retrieved contexts makes the prefill stage a dominant serving cost. RAG cache fusion reduces this cost by reusing precomputed key-value (KV) caches for retrieved chunks and selectively recomputing tokens under the current prompt.
arXiv:2606. 05875v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves large language model (LLM) answer quality by grounding generation in external evidence, but processing retrieved contexts makes the prefill stage a dominant serving cost.
Enterprise Document Intelligence [Vol. 1 #6c] - The decisions the parser makes on top of the user string, using the document’s profile: dispatch, activations, full schema, three approaches to deciding what fires, the audit _meta block, and a broker-corpus walkthrough The post Dispatching the Parsed RAG Question: Chunk Strategy, Model Tier, Activations, Audit appeared first on Towards Data Science .
ChunkRank is an open‑source Python library that automatically determines chunk boundaries based on a target model’s tokenizer and context window, and then selects an answer from independently produced chunk candidates. It includes a registry of 90 models from 15 providers and six answer‑selection methods, and requires only three core dependencies. Experiments show that token‑exact budgeting is important across 11 languages, and that for several datasets no content‑based ranker outperforms simply taking the first non‑empty answer due to reader abstention on chunks lacking the answer.
QESChunker introduces a supervised approach to construct static chunk indices for retrieval-augmented generation, using question–evidence pairs to guide the process. It unifies non‑overlapping and overlapping chunking under a single utility‑maximization objective, enabling exact polynomial‑time optimization for non‑overlap and a greedy approximation for overlap. Experiments on two self‑constructed and three public datasets show that both variants outperform existing methods in complete‑evidence recall across most settings.