HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions

• URL: http://arxiv.org/abs/2606.22778v1
• Date: Mon, 22 Jun 2026 02:42:06 GMT
• Title: HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions
• Abstract summary: We present HAKARI-Bench, a benchmark that reconstructs existing retrieval suites into small datasets (Nano-sets)<n>It enables same-condition, model-agnostic comparison of five retrieval families (BM25, dense, sparse, late interaction, rerankers) and their efficiency variants.<n>Its overall ranking reproduces the official MTEB retrieval v2, MMTEB v2 retrieval, and English BEIR (full) at Spearman >0.97.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the rapid spread of retrieval-augmented generation and semantic search, choosing the right embedding and retrieval configuration is increasingly hard. Large retrieval benchmarks are comprehensive but too heavy to rerun during development, and there is little infrastructure for comparing production settings--dimensionality reduction, quantization, reranking--across many models under identical conditions. We present HAKARI-Bench, a lightweight benchmark that reconstructs existing retrieval suites into small datasets (Nano-sets): 35 benchmarks and 551 tasks across 43 languages in a unified format, enabling same-condition, model-agnostic comparison of five retrieval families (BM25, dense, sparse, late interaction, rerankers) and their efficiency variants. Across 55 models, its overall ranking reproduces the official MTEB retrieval v2, MMTEB v2 retrieval, and English BEIR (full) at Spearman >0.97. HAKARI-Bench does not replace full evaluation; it enables rapid model selection, regression detection, and reading the quality-efficiency Pareto frontier. Code, data, and leaderboard are released under the MIT license.

Related papers

• Multimodal Hybrid Retrieval-Augmented Generation for Scientific Document Understanding using Open-Source SLMs [45.88028371034407]
  Large Language Models tend to hallucinate when answering domain-specific ques tions from scientific documents without prior fine-tuning.<n>This paper presents an Advanced Multimodal Retrieval-Augmented Generation system that aims to solve those challenges.<n>Results demonstrate a 157% improvement in retrieval quality over a Naive-RAG baseline, with only 50 ms additional la tency, while Qwen2-VL-2B-Instruct achieved results comparable to cloud-based models in BERTScore.
  arXiv  Detail & Related papers  (2026-07-06T08:32:09Z)
• Automating Formal Verification with Agent-Guided Tree Search [0.0]
  Formal verification offers a path to provably correct software, but writing verified code remains expensive enough that the technique is rarely used in production.<n>Recent benchmarks measure their ability to translate specifications into code and machine-checked iteration of correctness.<n>This thesis evaluates the state of such LLM-driven verified-code generation in Lean and develops search-based methods for improving performance.
  arXiv  Detail & Related papers  (2026-05-26T14:50:47Z)
• MultiHaystack: Benchmarking Multimodal Retrieval and Reasoning over 40K Images, Videos, and Documents [57.32877731797049]
  MultiHaystack is the first benchmark designed to evaluate both retrieval and reasoning under large-scale, cross-modal conditions.<n>We find that models perform competitively when provided with the corresponding evidence, but their performance drops sharply when required to retrieve that evidence from the full corpus.
  arXiv  Detail & Related papers  (2026-03-05T21:43:02Z)
• A-MapReduce: Executing Wide Search via Agentic MapReduce [29.20827525190302]
  A-MapReduce is a paradigm-inspired multi-agent execution framework.<n>It recasts wide search as a horizontally structured retrieval problem.<n>A-MapReduce is high-performing, achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-01T16:53:29Z)
• LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum [73.82125917416067]
  LACONIC is a family of learned sparse retrievers based on the Llama-3 architecture.<n>The 8B variant achieves a state-of-the-art 60.2 nDCG on the MTEB Retrieval benchmark, ranking 15th on the leaderboard.
  arXiv  Detail & Related papers  (2026-01-04T22:42:20Z)
• MR$^2$-Bench: Going Beyond Matching to Reasoning in Multimodal Retrieval [86.35779264575154]
  Multimodal retrieval is becoming a crucial component of modern AI applications, yet its evaluation lags behind the demands of more realistic and challenging scenarios.<n>We introduce MR$2$-Bench, a reasoning-intensive benchmark for multimodal retrieval.
  arXiv  Detail & Related papers  (2025-09-30T15:09:14Z)
• MMTEB: Massive Multilingual Text Embedding Benchmark [85.18187649328792]
  We introduce the Massive Multilingual Text Embedding Benchmark (MMTEB)<n>MMTEB covers over 500 quality-controlled evaluation tasks across 250+ languages.<n>We develop several highly multilingual benchmarks, which we use to evaluate a representative set of models.
  arXiv  Detail & Related papers  (2025-02-19T10:13:43Z)
• REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark [16.55516587540082]
  We introduce REAL-MM-RAG, an automatically generated benchmark designed to address four key properties essential for real-world retrieval.<n>We propose a multi-difficulty-level scheme based on query rephrasing to evaluate models' semantic understanding beyond keyword matching.<n>Our benchmark reveals significant model weaknesses, particularly in handling table-heavy documents and robustness to query rephrasing.
  arXiv  Detail & Related papers  (2025-02-17T22:10:47Z)
• CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval [103.116634967815]
  We introduce CodeXEmbed, a family of large-scale code embedding models ranging from 400M to 7B parameters.<n>Our novel training pipeline unifies multiple programming languages and transforms various code-related tasks into a common retrieval framework.<n>Our 7B model sets a new state-of-the-art (SOTA) in code retrieval, outperforming the previous leading model, Voyage-Code, by over 20% on CoIR benchmark.
  arXiv  Detail & Related papers  (2024-11-19T16:54:45Z)
• Text Embeddings by Weakly-Supervised Contrastive Pre-training [98.31785569325402]
  E5 is a family of state-of-the-art text embeddings that transfer well to a wide range of tasks. E5 can be readily used as a general-purpose embedding model for any tasks requiring a single-vector representation of texts.
  arXiv  Detail & Related papers  (2022-12-07T09:25:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.