Builds a 2M-contribution graph from 230k papers with 12.5M prerequisite links and reports 0.48 MAP on temporal backtesting for predicting enabling technologies.
hub Canonical reference
Human-LLM Compound System for Scientific Ideation through Facet Recombination and Novelty Evaluation
Canonical reference. 83% of citing Pith papers cite this work as background.
14
Pith papers citing it
Background
83% of classified citations
abstract
The scientific ideation process often involves blending facets of existing papers to create new ideas. We contribute Scideator, the first human-LLM system for facet-based scientific ideation. Starting from user-provided papers, Scideator extracts key facets -- purposes, mechanisms, and evaluations -- from these and related papers, allowing users to interactively recombine facets to synthesize ideas. Scideator is driven by three design choices: (1) human-in-the-loop facet recombination, in which users select facets from retrieved papers and the system generates ideas by finding analogies across them via the Faceted Idea Generator module; (2) distance-controlled retrieval via the Analogous Paper Facet Finder module, which surfaces papers ranging from the same topic to entirely different areas to provide a spectrum of directions; and (3) facet-based novelty verification via the Idea Novelty Checker module, a retrieve-then-rerank pipeline that helps users to evaluate idea originality using facets. In a user study with computer science researchers, Scideator provided significantly more creativity support than a baseline using the same backbone LLM without our facet-based modules, particularly in idea exploration and expressiveness. Ablations further show that the facets benefit the novelty checker: facet-based retrieve-then-rerank surfaces more relevant papers than standard retrieval and re-ranking, and a facet-grounded novelty classifier outperforms classifiers that reason over unstructured ideas and papers.
hub tools
citation-role summary
background 6
citation-polarity summary
roles
background 6representative citing papers
EIG represents research ideas as evolving graphs with nodes for claims and edges for relations, using a learned controller for edits and commits to produce higher-quality scientific proposals than text-only multi-agent baselines.
ResearchCube provides a 3D spatial interface with bipolar trade-off dimensions and direct-manipulation interactions to support multi-dimensional research ideation, shown helpful in a study with 11 researchers for externalizing thinking and increasing agency.
LitPivot introduces literature-initiated pivots where engagement with dynamically retrieved papers prompts revisions to a developing research idea.
A framework decomposes LLM papers into idea atoms, trains coherence and availability models over the resulting vocabulary, and samples atom combinations that are coherent yet unlikely under existing author communities.
CHIMERA is the first large-scale mined KB of concept recombinations from scientific literature, created via a new IE task and LLM extraction, with demonstrated uses in pattern analysis and hypothesis generation.
AI peer review systems are vulnerable to prompt injections, prestige biases, assertion strength effects, and contextual poisoning, as demonstrated by a new attack taxonomy and causal experiments on real conference submissions.
Attribution gradients consolidate citation evidence and enable incremental unfolding of secondary sources, leading to deeper engagement in a lab study of critical reading tasks for AI answers.
LLM assistance shortens idea-generation periods and reduces creative moments during programming tasks while yielding solutions with comparable idea counts and greater functional correctness.
ECHO presents a multimodal co-editing system and CoEdit-Eval framework that improves AI intent mapping and spatial grounding for presentation refinement while reducing user cognitive load in a small study.
A survey organizing AI-powered research automation into five workflow stages, defining AutoResearch and Vibe Research, and proposing five evaluation dimensions while noting domain-conditioned limits on autonomy.
Omakase monitors project documents to infer timely queries and distills research reports into actionable suggestions that users rated significantly more useful than raw reports.
The paper proposes a four-role framework for LLMs in scientific innovation and reviews methods, benchmarks, and limitations across Assistant, Collaborator, Scientist, and Evaluator roles.
citing papers explorer
-
Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator
The paper proposes a four-role framework for LLMs in scientific innovation and reviews methods, benchmarks, and limitations across Assistant, Collaborator, Scientist, and Evaluator roles.