arXiv AI
Jul 3
PreScience: A Dataset and Benchmark for Scientific Forecasting
arXiv:2602. 20459v2 Announce Type: replace Abstract: Can AI systems trained on the existing scientific record forecast the advances that will follow?
Asymmetric Within-Document Predictive Learning for Scientific Document Representation
Related stories
arXiv Computation and Language
Aug 25
How Does Research Evolve? Tracing Cross-Domain Trajectories in NLP, ML, and CV Through Claim-Grounded Typed Citations
arXiv:2606.22342v2 Announce Type: replace Abstract: How does research evolve, and can we trace it at the level of individual claims? Scientific progress is not simply a uniform accumulation of facts....
arXiv Computation and Language
Sep 18
Improving Cross-Lingual Transfer for Sequential Sentence Classification in Research Papers via Structural Similarity
The paper investigates cross‑lingual transfer for sequential sentence classification (SSC) in research papers, focusing on 13 non‑English languages. Experiments show that linguistic proximity does not reliably predict transfer success, whereas structural similarity in rhetorical organization—particularly label distribution similarity—correlates positively with performance. The authors introduce three generative‑model methods that exploit structural cues, achieving parity with strong encoder baselines on‑domain and outperforming them when transferring to unseen languages.
Hugging Face Trending Papers
Jun 23
Less is More: Quality-Aware Training Data Selection for Scientific Summarization
Scientific long-document summarization datasets commonly treat author-written abstracts as gold reference summaries, although their quality and alignment with the source article vary. At the same time, publicly available scientific summarization datasets remain limited in scale and structure for modern long-context models.
arXiv Computation and Language
Sep 22
NLPCC 2026 Task 10: Citation-Level Faithfulness Verification with DeBERTa Ensembles and Class-Wise Calibration
arXiv:2609.22774v1 Announce Type: new Abstract: This paper presents our system for Track 2 of the NLPCC 2026 Shared Task 10 on citation-level faithfulness in AI-assisted scientific reporting. Given a...
arXiv AI
Jul 9
RWGBench: Evaluating Scholarly Positioning in Related Work Generation
arXiv:2606. 24894v2 Announce Type: replace-cross Abstract: Large language models have shown strong fluency in scientific writing, yet the evaluation of related work generation (RWG) remains limited.
arXiv AI
Sep 25
Learning to Ideate for Scientific Impact
The paper "Learning to Ideate for Scientific Impact" explores using delayed signals of scientific uptake—specifically citation-normalized impact—as feedback to steer large language models toward generating high‑impact research ideas. The authors build a dataset of over 100,000 computer science papers, train a reward model to predict citation impact from goal‑idea pairs, and align an idea generator via supervised fine‑tuning and reinforcement learning. Evaluation with a reference‑grounded protocol shows that the RL‑tuned model consistently produces ideas with higher estimated impact than baseline models.
arXiv AI
Aug 5
SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG
arXiv:2608. 03860v1 Announce Type: cross Abstract: We introduce SciRet, a compute-aware empirical study of retrieval-augmented generation for scientific question answering over CORD-19.
Hugging Face Trending Papers
Jun 24
Automatic Generation of Highlights for Academic Paper Via Prompt-based Learning
Highlights provide a concise summary of the main contributions of an academic paper and help readers quickly understand its focus. However, many journals do not provide highlights, which limits their use in literature retrieval, text mining, and bibliometric analysis.
Hugging Face Trending Papers
Jun 2
Re-Ranking Through an Attribution Lens for Citation Quality in Legal QA
Retrieval-augmented generation systems for legal question answering typically retrieve passages based on semantic similarity and provide them to a language model, which then generates cited answers. Prior work assumes that highly ranked passages are most likely to be usefully cited by the model.
Hugging Face Trending Papers
Jun 21
How Does Research Evolve? Tracing Cross-Domain Trajectories in NLP, ML, and CV with Claim-Grounded Typed Citations
How does research evolve, and what substrate would let us forecast where it goes next? Scientific progress is not simply a uniform accumulation of facts: ideas extend prior methods, address known limitations, realize proposed future directions, and sometimes dispute earlier claims.
arXiv Computation and Language
Aug 28
RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature
RATIO (Retrieval Across Typed Ideation Operations) is a large-scale benchmark designed to evaluate how well retrieval systems can support scientific inspiration. It defines relevance through three ideation moves—Address, Broaden, and Specify—each targeting different levels of abstraction in literature retrieval. The benchmark is built from millions of full-text CS papers using a novel discourse-marker distant supervision method, and includes extensive LLM and human vetting to ensure quality.