Zobrazeno 1 - 10
of 808
pro vyhledávání: '"P. Zamfirescu"'
Autor:
Jooken, Jorik, Zamfirescu, Carol T.
We show that there exists an infinite family of cubic $2$-connected non-hamiltonian graphs with girth at least $5$ containing a unique longest cycle.
Externí odkaz:
http://arxiv.org/abs/2409.17205
Small-group tutoring in Computer Science (CS) is effective, but presents the challenge of providing a dedicated tutor for each group and encouraging collaboration among group members at scale. We present Pensieve Discuss, a software platform that int
Externí odkaz:
http://arxiv.org/abs/2407.17007
Chatbot interfaces for LLMs enable students to get immediate, interactive help on homework assignments, but even a thoughtfully-designed bot may not serve all pedagogical goals. In this paper, we report on the development and deployment of a GPT-4-ba
Externí odkaz:
http://arxiv.org/abs/2406.05600
Autor:
Qi, Laryn, Zamfirescu-Pereira, J. D., Kim, Taehan, Hartmann, Björn, DeNero, John, Norouzi, Narges
We evaluate an automatic hint generator for CS1 programming assignments powered by GPT-4, a large language model. This system provides natural language guidance about how students can improve their incorrect solutions to short programming exercises.
Externí odkaz:
http://arxiv.org/abs/2406.05603
Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences
Autor:
Shankar, Shreya, Zamfirescu-Pereira, J. D., Hartmann, Björn, Parameswaran, Aditya G., Arawjo, Ian
Due to the cumbersome nature of human evaluation and limitations of code-based evaluation, Large Language Models (LLMs) are increasingly being used to assist humans in evaluating LLM outputs. Yet LLM-generated evaluators simply inherit all the proble
Externí odkaz:
http://arxiv.org/abs/2404.12272
Autor:
Lin, Susan, Warner, Jeremy, Zamfirescu-Pereira, J. D., Lee, Matthew G., Jain, Sauhard, Huang, Michael Xuelin, Lertvittayakumjorn, Piyawat, Cai, Shanqing, Zhai, Shumin, Hartmann, Björn, Liu, Can
Dictation enables efficient text input on mobile devices. However, writing with speech can produce disfluent, wordy, and incoherent text and thus requires heavy post-processing. This paper presents Rambler, an LLM-powered graphical user interface tha
Externí odkaz:
http://arxiv.org/abs/2401.10838
In a given graph, a HIST is a spanning tree without $2$-valent vertices. Motivated by developing a better understanding of HIST-free graphs, i.e. graphs containing no HIST, in this article's first part we study HIST-critical graphs, i.e. HIST-free gr
Externí odkaz:
http://arxiv.org/abs/2401.04554
Autor:
Shankar, Shreya, Li, Haotian, Asawa, Parth, Hulsebos, Madelon, Lin, Yiming, Zamfirescu-Pereira, J. D., Chase, Harrison, Fu-Hinthorn, Will, Parameswaran, Aditya G., Wu, Eugene
Large language models (LLMs) are being increasingly deployed as part of pipelines that repeatedly process or generate data of some sort. However, a common barrier to deployment are the frequent and often unpredictable errors that plague LLMs. Acknowl
Externí odkaz:
http://arxiv.org/abs/2401.03038
Autor:
Noguchi, Kenta, Zamfirescu, Carol T.
Let $G$ be a connected graph and $L(G)$ the set of all integers $k$ such that $G$ contains a spanning tree with exactly $k$ leaves. We show that for a connected graph $G$, the set $L(G)$ is contiguous. It follows from work of Chen, Ren, and Shan that
Externí odkaz:
http://arxiv.org/abs/2312.13674
We present an algorithm which can generate all pairwise non-isomorphic $K_2$-hypohamiltonian graphs, i.e. non-hamiltonian graphs in which the removal of any pair of adjacent vertices yields a hamiltonian graph, of a given order. We introduce new boun
Externí odkaz:
http://arxiv.org/abs/2311.10593