中文
相关论文

相关论文: Evaluating and Enhancing Large Language Models for…

200 篇论文

Novelty is a core requirement in academic publishing and a central focus of peer review, yet the growing volume of submissions has placed increasing pressure on human reviewers. While large language models (LLMs), including those fine-tuned…

计算与语言 · 计算机科学 2026-04-14 Wenqing Wu , Yi Zhao , Yuzhuo Wang , Siyou Li , Juexi Shao , Yunfei Long , Chengzhi Zhang

Novelty is a crucial criterion in the peer review process for evaluating academic papers. Traditionally, it's judged by experts or measure by unique reference combinations. Both methods have limitations: experts have limited knowledge, and…

计算与语言 · 计算机科学 2025-07-17 Wenqing Wu , Chengzhi Zhang , Yi Zhao

Judging the novelty of research ideas is crucial for advancing science, enabling the identification of unexplored directions, and ensuring contributions meaningfully extend existing knowledge rather than reiterate minor variations. However,…

计算与语言 · 计算机科学 2026-03-12 Tim Schopf , Michael Färber

Large language models such as ChatGPT have increased scholarly output, but whether this productivity boost produces genuine intellectual advancement remains untested. I address this gap by measuring the semantic novelty of 13,847 articles…

数字图书馆 · 计算机科学 2026-03-25 Ali Safari

Automated scientific idea generation systems have made remarkable progress, yet the automatic evaluation of idea novelty remains a critical and underexplored challenge. Manual evaluation of novelty through literature review is…

信息检索 · 计算机科学 2025-06-30 Simra Shahid , Marissa Radensky , Raymond Fok , Pao Siangliulue , Daniel S. Weld , Tom Hope

The accelerating pace of scientific publication makes it difficult to identify truly original research among incremental work. We propose a framework for estimating the conceptual novelty of research papers by combining semantic…

机器学习 · 计算机科学 2026-01-06 Zhengxu Yan , Han Li , Yuming Feng

Novelty assessment is a central yet understudied aspect of peer review, particularly in high volume fields like NLP where reviewer capacity is increasingly strained. We present a structured approach for automated novelty evaluation that…

计算与语言 · 计算机科学 2026-01-21 Osama Mohammed Afzal , Preslav Nakov , Tom Hope , Iryna Gurevych

Novelty, akin to gene mutation in evolution, opens possibilities for scholarly advancement. Although peer review remains the gold standard for evaluating novelty in scholarly communication and resource allocation, the vast volume of…

计算与语言 · 计算机科学 2024-01-17 Haining Wang

Evaluating novelty is critical yet challenging in peer review, as reviewers must assess submissions against a vast, rapidly evolving literature. This report presents OpenNovelty, an LLM-powered agentic system for transparent, evidence-based…

Large Language Models (LLMs) show strong reasoning and text generation capabilities, prompting their use in scientific literature analysis, including novelty assessment. While evaluating novelty of scientific papers is crucial for peer…

信息检索 · 计算机科学 2025-10-20 Italo Luis da Silva , Hanqi Yan , Lin Gui , Yulan He

As large language models (LLMs) are increasingly used for ideation and scientific discovery, it is important to evaluate their ability to generate novel output. Prior work evaluates novelty as originality with respect to model training…

计算与语言 · 计算机科学 2025-10-08 Vishakh Padmakumar , Chen Yueh-Han , Jane Pan , Valerie Chen , He He

In an era of exponential scientific growth, identifying novel research ideas is crucial and challenging in academia. Despite potential, the lack of an appropriate benchmark dataset hinders the research of novelty detection. More…

计算与语言 · 计算机科学 2025-06-02 Yan Liu , Zonglin Yang , Soujanya Poria , Thanh-Son Nguyen , Erik Cambria

Recent advancements in large language models (LLMs) have sparked optimism about their potential to accelerate scientific discovery, with a growing number of works proposing research agents that autonomously generate and validate new ideas.…

计算与语言 · 计算机科学 2024-09-09 Chenglei Si , Diyi Yang , Tatsunori Hashimoto

Assessing originality in AI research is arguably the most consequential yet least reliable step in peer review. Reviewer judgments of originality remain opaque, inconsistent, and dependent on comparisons to prior work that are often…

计算与语言 · 计算机科学 2026-05-28 Abeer Mostafa , Thi Huyen Nguyen , Zahra Ahmadi

The widespread adoption of Large Language Models (LLMs) and publicly available ChatGPT have marked a significant turning point in the integration of Artificial Intelligence (AI) into people's everyday lives. This study examines the ability…

计算与语言 · 计算机科学 2025-10-28 Sandeep Kumar , Tirthankar Ghosal , Vinayak Goyal , Asif Ekbal

Novelty evaluation is vital for the promotion and management of innovation. With the advancement of information techniques and the open data movement, some progress has been made in novelty measurements. Tracking and reviewing novelty…

数字图书馆 · 计算机科学 2025-01-30 Yi Zhao , Chengzhi Zhang

Previous work has demonstrated that AI methods for analysing scientific literature benefit significantly from annotating sentences in papers according to their rhetorical roles, such as research gaps, results, limitations, extensions of…

计算与语言 · 计算机科学 2026-02-11 Francisco Bolaños , Angelo Salatino , Francesco Osborne , Enrico Motta

Academic paper review typically requires substantial time, expertise, and human resources. Large Language Models (LLMs) present a promising method for automating the review process due to their extensive training data, broad knowledge base,…

计算机与社会 · 计算机科学 2025-06-24 Chuanlei Li , Xu Hu , Minghui Xu , Kun Li , Yue Zhang , Xiuzhen Cheng

Language models have demonstrated remarkable capabilities on standard benchmarks, yet they struggle increasingly from mode collapse, the inability to generate diverse and novel outputs. Our work introduces NoveltyBench, a benchmark…

计算与语言 · 计算机科学 2025-08-12 Yiming Zhang , Harshita Diddee , Susan Holm , Hanchen Liu , Xinyue Liu , Vinay Samuel , Barry Wang , Daphne Ippolito

Despite impressive results on curated benchmarks, the practical impact of large language models (LLMs) on research-level neural theorem proving and proof autoformalization is still limited. We introduce RLMEval, an evaluation suite for…

计算与语言 · 计算机科学 2025-10-30 Auguste Poiroux , Antoine Bosselut , Viktor Kunčak
‹ 上一页 1 2 3 10 下一页 ›