RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature

• URL: http://arxiv.org/abs/2608.27394v3
• Date: Tue, 01 Sep 2026 11:22:32 GMT
• Title: RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature
• Abstract summary: RATIO is a large-scale benchmark in which relevance is defined by three operations.<n>RATIO is constructed from millions of full-text scientific papers across CS literature.
• Score: 7.529978082645584
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Retrieved scientific literature can serve as inspiration for both human and AI scientists. Inspiration can take different forms: prior work may directly suggest how to address a problem, or surface directions at different levels of abstraction - zooming out to a more general view or zooming in to a concrete realization. We introduce RATIO (Retrieval Across Typed Ideation Operations), a large-scale benchmark in which relevance is defined by three operations which we name ideation moves: Address retrieves potential approaches for stated problems, Broaden retrieves more general formulations, and Specify retrieves concrete instantiations. RATIO is constructed from millions of full-text scientific papers across CS literature via a general recipe that extends discourse-marker distant supervision - previously used only for classification - to corpus-scale retrieval, combined with extensive LLM and human vetting. Experiments show that operation-specific fine-tuning substantially boosts retrievers but leaves much room for further improvements. RATIO provides a scalable training and evaluation framework for retrieval components that support literature-grounded ideation, opening up new research avenues on scientific inspiration retrieval.

Related papers

• Extending AI for Research to the Humanities: A Multi-Agent Framework for Evidence-Grounded Scholarship [16.735903349022777]
  SPIRE (Scholarly-Primitives-Inspired Research Engine) is a multi-agent framework for evidence-grounded humanities scholarship.<n>It casts recurring humanities operations as cooperating agent roles over a multi-scale close-reading substrate.<n>It receives higher blind-judge scores on answer accuracy, depth, coverage, and evidence quality.
  arXiv  Detail & Related papers  (2026-05-29T07:33:29Z)
• Reward Modeling for Scientific Writing Evaluation [50.33952894976367]
  It is critical to develop models that can be reliably deployed for evaluating diverse open-ended scientific writing tasks.<n>We propose cost-efficient, open-source reward models tailored for scientific writing evaluation.
  arXiv  Detail & Related papers  (2026-01-16T15:32:58Z)
• Dr.Mi-Bench: A Modular-integrated Benchmark for Scientific Deep Research Agent [52.876617746453995]
  Dr.Mi-Bench is a Modular-integrated benchmark for scientific deep research (DR) agents.<n>Dr.Mi-Eval is a novel modular-integrated evaluation paradigm.
  arXiv  Detail & Related papers  (2025-11-30T17:16:47Z)
• CASPER: Concept-integrated Sparse Representation for Scientific Retrieval [17.680327408224237]
  We propose CASPER, a sparse retrieval model for scientific search that utilizes tokens and keyphrases as representation units.<n>We show that CASPER can be effectively used for the keyphrase generation tasks, achieving competitive performance with the established CopyRNN.
  arXiv  Detail & Related papers  (2025-08-18T23:00:57Z)
• Can LLMs Generate Tabular Summaries of Science Papers? Rethinking the Evaluation Protocol [83.90769864167301]
  Literature review tables are essential for summarizing and comparing collections of scientific papers.<n>We explore the task of generating tables that best fulfill a user's informational needs given a collection of scientific papers.<n>Our contributions focus on three key challenges encountered in real-world use: (i) User prompts are often under-specified; (ii) Retrieved candidate papers frequently contain irrelevant content; and (iii) Task evaluation should move beyond shallow text similarity techniques.
  arXiv  Detail & Related papers  (2025-04-14T14:52:28Z)
• Large Language Model Can Be a Foundation for Hidden Rationale-Based Retrieval [12.83513794686623]
  In this paper, we propose and study a more challenging type of retrieval task, called hidden rationale retrieval.<n>To address such problems, an instruction-tuned Large language model (LLM) with a cross-encoder architecture could be a reasonable choice.<n>We name this retrieval framework by RaHoRe and verify its zero-shot and fine-tuned performance superiority on Emotional Support Conversation (ESC)
  arXiv  Detail & Related papers  (2024-12-21T13:19:15Z)
• Enhancing LLM Reasoning with Reward-guided Tree Search [95.06503095273395]
  o1-like reasoning approach is challenging, and researchers have been making various attempts to advance this open area of research.<n>We present a preliminary exploration into enhancing the reasoning abilities of LLMs through reward-guided tree search algorithms.
  arXiv  Detail & Related papers  (2024-11-18T16:15:17Z)
• SciPIP: An LLM-based Scientific Paper Idea Proposer [30.670219064905677]
  We introduce SciPIP, an innovative framework designed to enhance the proposal of scientific ideas through improvements in both literature retrieval and idea generation.<n>Our experiments, conducted across various domains such as natural language processing and computer vision, demonstrate SciPIP's capability to generate a multitude of innovative and useful ideas.
  arXiv  Detail & Related papers  (2024-10-30T16:18:22Z)
• ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models [56.08917291606421]
  ResearchAgent is an AI-based system for ideation and operationalization of novel work.<n>ResearchAgent automatically defines novel problems, proposes methods and designs experiments, while iteratively refining them.<n>We experimentally validate our ResearchAgent on scientific publications across multiple disciplines.
  arXiv  Detail & Related papers  (2024-04-11T13:36:29Z)
• Retrieval Augmentation for Commonsense Reasoning: A Unified Approach [64.63071051375289]
  We propose a unified framework of retrieval-augmented commonsense reasoning (called RACo) Our proposed RACo can significantly outperform other knowledge-enhanced method counterparts.
  arXiv  Detail & Related papers  (2022-10-23T23:49:08Z)

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.