Pith. sign in

REVIEW 4 cited by

SciRepEval: A Multi-Format Benchmark for Scientific Document Representations

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2211.13308 v4 pith:N2TN6RHC submitted 2022-11-23 cs.CL cs.AIcs.IRcs.LG

SciRepEval: A Multi-Format Benchmark for Scientific Document Representations

classification cs.CL cs.AIcs.IRcs.LG
keywords documentrepresentationsscientificbenchmarkimprovemodelstasksacross
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Learned representations of scientific documents can serve as valuable input features for downstream tasks without further fine-tuning. However, existing benchmarks for evaluating these representations fail to capture the diversity of relevant tasks. In response, we introduce SciRepEval, the first comprehensive benchmark for training and evaluating scientific document representations. It includes 24 challenging and realistic tasks, 8 of which are new, across four formats: classification, regression, ranking and search. We then use this benchmark to study and improve the generalization ability of scientific document representation models. We show how state-of-the-art models like SPECTER and SciNCL struggle to generalize across the task formats, and that simple multi-task training fails to improve them. However, a new approach that learns multiple embeddings per document, each tailored to a different format, can improve performance. We experiment with task-format-specific control codes and adapters and find they outperform the existing single-embedding state-of-the-art by over 2 points absolute. We release the resulting family of multi-format models, called SPECTER2, for the community to use and build on.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes

    cs.AI 2026-07 conditional novelty 7.0

    Conference accept/reject outcomes yield 15 operational ideation patterns that, as an LLM skill suite, improve automated-judged research-proposal quality over no-skill and generic-skill baselines.

  2. Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation

    cs.CL 2026-05 unverdicted novelty 7.0

    GoR extracts citation DAGs using position, frequency, predecessor links and time, then fine-tunes Qwen2.5-7B on 498 seed papers to generate ideas, claiming SOTA over gpt-4o baselines via LLM judges.

  3. Re$^2$Math: Benchmarking Theorem Retrieval in Research-Level Mathematics

    cs.AI 2026-05 unverdicted novelty 7.0

    Re²Math is a new benchmark that evaluates AI models on retrieving and verifying the applicability of theorems from math literature to advance steps in partial proofs, accepting any sufficient theorem while controlling...

  4. Translating AI into scientific impact: Field context, career position, and institutional capability in AI-enabled research

    cs.CY 2026-07 conditional novelty 5.0

    Citing AI literature is tied to higher citation impact overall, yet field, career stage, and institutional AI capability redistribute that benefit, with intermediate-capability institutions gaining the most per unit o...