Retrieval pipelines are being reshaped by compact legal embeddings, BM25 resurgences, KV cache reuse and memory-format studies. These efforts aim to make semantic search and RAG more accurate and deployable without massive infrastructure.
An architecture combines a topology GNN with a parameter-efficient small language model to select and route messages in labeled property graphs. A bounded residual update to the structural anchor preserves interpretability and opens the door to local...
A 0.6 billion parameter legal embedding model shows that distillation, hard negative mining, and binary quantization can move legal retrieval toward self-hosted deployments. The structural issue is not benchmark performance alone, but the ability to ...
A study on collaborative conversations shows that the semantic similarity of generated replies changes with model and chat history. Prompts and context alone cannot preserve consistency; infrastructure and design strategies are needed for stable, com...
GreenLeaf Law Embed Tiny is a 0.6B parameter embedding model for legal retrieval. It achieves 75.11% on MLEB and 64.38% on MTEB Law. Its two-stage pipeline combines distillation and fine-tuning with hard negative mining on 3.4 million query-passage p...
RENDER introduces a control for evaluating memory in LLMs: it fixes the conversation and varies the reader-facing artifact. Across 500 LongMemEval questions and nine models, matched-budget resolved packets beat recency-truncated raw dialogue by 42.4–...
A study on 3,000 Khmer documents shows BM25 outperforms dense retrieval and Qwen2.5-assisted query expansion. The larger model produces better expansions but still introduces noise. A signal for teams building low-cost local search.
KVBoost reuses key-value cache at chunk level and reduces time-to-first-token by 4.49x on Qwen2.5-3B, with no accuracy loss. Unlike prefix caching, it does not require a shared leading prefix: a dual hash separates positional and content identity. As...
