Related papers: An Update to the Minho Quotation Resource
We provide compact algebraic expressions that replace the lengthy symbolic-algebra-generated integrals I6 and I8 in Part I of this series of papers [1]. The MRSE entries of Part I, Table 4.3 are thus updated to simpler algebraic…
We introduce SelfCite, a novel self-supervised approach that aligns LLMs to generate high-quality, fine-grained, sentence-level citations for the statements in their generated responses. Instead of only relying on costly and labor-intensive…
Disturbances in the job market such as advances in science and technology, crisis and increased competition have triggered a surge in reskilling and upskilling programs. Information on suitable continuing education options is distributed…
The semiconductor industry is foundational to modern technology, yet its complex global multi-relational firm network remains poorly understood, posing challenges to scientists, firms, and policymakers. Traditional analysis relies on…
We present the Twitter Job/Employment Corpus, a collection of tweets annotated by a humans-in-the-loop supervised learning framework that integrates crowdsourcing contributions and expertise on the local community and employment…
This paper introduces two novel modifications to the Dynamic sAmpling Policy Optimization (DAPO) algorithm [1], approached from a mixed-policy perspective. Standard policy gradient methods can suffer from instability and sample…
We present a new corpus with coreference annotation, Russian Coreference Corpus (RuCoCo). The goal of RuCoCo is to obtain a large number of annotated texts while maintaining high inter-annotator agreement. RuCoCo contains news texts in…
We computed linguistic information at the lexical, syntactic, and semantic levels for Recognizing Inference in Text (RITE) tasks for both traditional and simplified Chinese in NTCIR-9 and NTCIR-10. Techniques for syntactic parsing,…
The role of credit rating agencies has been under severe scrutiny after the subprime crisis. In this paper we explore the relationship between credit ratings and informational efficiency of a sample of thirty nine corporate bonds of US oil…
Chinese, as a linguistic system rich in depth and complexity, is characterized by distinctive elements such as ancient poetry, proverbs, idioms, and other cultural constructs. However, current Large Language Models (LLMs) face limitations…
The present research attempts to identify the impact of retracted papers on previous or subsequent papers. We consider the 5693 retracted papers from 1975 to 2020 indexed in the Web of Science database based on bibliometric methods. We use…
Several recent papers claim human parity at sentence-level Machine Translation (MT), especially in high-resource languages. Thus, in response, the MT community has, in part, shifted its focus to document-level translation. Translating…
Language Models (LMs) become outdated as the world changes; they often fail to perform tasks requiring recent factual information which was absent or different during training, a phenomenon called temporal misalignment. This is especially a…
In over five years, Bornmann, Stefaner, de Moya Anegon, and Mutz (2014) and Bornmann, Stefaner, de Moya Anegon, and Mutz (2014, 2015) have published several releases of the www.excellencemapping.net tool revealing (clusters of) excellent…
Textual knowledge bases such as Wikipedia require considerable effort to keep up to date and consistent. While automated writing assistants could potentially ease this burden, the problem of suggesting edits grounded in external knowledge…
In this work, we introduce the MOldavian and ROmanian Dialectal COrpus (MOROCO), which is freely available for download at https://github.com/butnaruandrei/MOROCO. The corpus contains 33564 samples of text (with over 10 million tokens)…
Engineering and materials software is increasingly difficult to track in the scholarly and technical literature because publication volume is growing rapidly and software citation practices remain inconsistent. This is particularly true for…
We have implemented the Memento MediaWiki Extension Version 2.0, which brings the Memento Protocol to MediaWiki, used by Wikipedia and the Wikimedia Foundation. Test results show that the extension has a negligible impact on performance.…
We propose MINT, a new Multilingual INTimacy analysis dataset covering 13,372 tweets in 10 languages including English, French, Spanish, Italian, Portuguese, Korean, Dutch, Chinese, Hindi, and Arabic. We benchmarked a list of popular…
Reinforcement learning for multi-step reasoning with large language models (LLMs) typically relies on sparse terminal rewards, which creates a poorly conditioned credit-assignment problem: the final feedback is propagated uniformly across…