Viraj Kumar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Viraj Kumar has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Paul Denny
University of Auckland, Auckland, New Zealand
8 shared publications - Arun Raman
Birla Institute of Technology and Science, Goa, India
4 shared publications - Juho Leinonen
Aalto University, Espoo, Finland
4 shared publications - James Prather
Abilene Christian University, Abilene, TX, USA
3 shared publications - Stephen MacNeil
Temple University, Philadelphia, PA, USA
3 shared publications - Amrit M. Joseph
Indian Institute of Science, India
2 shared publications
Latest Publications
- Open Access
- 11 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 143-149
Commenting with Copilot: A Taxonomy and Multi-Year Analysis of Student Code-Generation Specifications
- 11 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 143-149
Open AccessCommenting with Copilot: A Taxonomy and Multi-Year Analysis of Student Code-Generation Specifications
- Open Access
- 17 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1635-1636
ACM Generative AI Task Force Special Session: Teaching with Generative AI: Tools You Can Use Today
- 17 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1635-1636
Open AccessACM Generative AI Task Force Special Session: Teaching with Generative AI: Tools You Can Use Today
- Open Access
- 9 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 182-191
Unraveling Ambiguities: Analyzing Student Approaches to Solving Probeable Problems
- 9 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 182-191
Open AccessUnraveling Ambiguities: Analyzing Student Approaches to Solving Probeable Problems
- 23 October 2025
- Published by Springer Nature
- p. 177-188
How Effectively Can Off-the-Shelf Generative AI Tools Solve Circuit Design Problems?
- 23 October 2025
- Published by Springer Nature
- p. 177-188
How Effectively Can Off-the-Shelf Generative AI Tools Solve Circuit Design Problems?
- Open Access
Ambiguity Resolution with Human Feedback for Code Writing Tasks
Specifications for code writing tasks are usually expressed in natural language and may be ambiguous. Programmers must therefore develop the ability to recognize ambiguities in task specifications and resolve them by asking clarifying questions. We present and evaluate a prototype system, based on a novel technique (ARHF: Ambiguity Resolution with Human Feedback), that (1) suggests specific inputs on which a given task specification may be ambiguous, (2) seeks limited human feedback about the code's desired behavior on those inputs, and (3) uses this feedback to generate code that resolves these ambiguities. We evaluate the efficacy of our prototype, and we discuss the implications of such assistive systems on Computer Science education.
Open AccessAmbiguity Resolution with Human Feedback for Code Writing Tasks
Specifications for code writing tasks are usually expressed in natural language and may be ambiguous. Programmers must therefore develop the ability to recognize ambiguities in task specifications and resolve them by asking clarifying questions. We present and evaluate a prototype system, based on a novel technique (ARHF: Ambiguity Resolution with Human Feedback), that (1) suggests specific inputs on which a given task specification may be ambiguous, (2) seeks limited human feedback about the code's desired behavior on those inputs, and (3) uses this feedback to generate code that resolves these ambiguities. We evaluate the efficacy of our prototype, and we discuss the implications of such assistive systems on Computer Science education.
- Open Access
- 13 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 618-624
Probing the Unknown: Exploring Student Interactions with Probeable Problems at Scale in Introductory Programming
- 13 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 618-624
Open AccessProbing the Unknown: Exploring Student Interactions with Probeable Problems at Scale in Introductory Programming
- Open Access
- 13 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 30-36
Refuting LLM-generated Code with Reactive Task Comprehension
- 13 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 30-36
Open AccessRefuting LLM-generated Code with Reactive Task Comprehension
- 13 March 2025
- Published by Springer Nature
- p. 3-17
Explain in Plain Language Questions with Indic Languages: Drawbacks, Affordances, and Opportunities
- 13 March 2025
- Published by Springer Nature
- p. 3-17
Explain in Plain Language Questions with Indic Languages: Drawbacks, Affordances, and Opportunities
- 13 March 2025
- Published by Springer Nature
- p. 83-96
RECE: A Family of Explainable Rubrics for Autograding Refute Problems
- 13 March 2025
- Published by Springer Nature
- p. 83-96
RECE: A Family of Explainable Rubrics for Autograding Refute Problems
- Open Access
Explain in Plain Language Questions with Indic Languages: Drawbacks, Affordances, and Opportunities
Background: Introductory computer science courses use ``Explain in Plain English'' (EiPE) activities to develop and assess students' code comprehension skills, but creating effective autograders for these questions is challenging and limited to English. This is a particular challenge in linguistically diverse countries like India where students may have limited proficiency in English. Methods: We evaluate the efficacy of a recently introduced approach called Code Generation Based Grading (CGBG) in enabling language agnostic ``Explain in Plain Language'' (EiPL) activities. Here students' EiPL responses generate code that is tested for functional equivalence to the original which was being described. Objectives: We initially evaluate the correctness of code generated from correct EiPL responses provided in 10 of India's most commonly spoken languages. To evaluate the effectiveness of the approach in practice, we assess student success and perceptions of EiPL questions in a NPTEL (National Programme on Technology Enhanced Learning) course. Results: We find promising results for the correctness of code generated from translations of correct EiPL responses, with most languages achieving a correctness rate of 75% or higher. However, in practice, many students preferred to respond in English due to greater familiarity with English as a technical language, difficulties writing in their native language, and perceptions of the grader being less capable of generating code from prompts in their mother tongue.
Open AccessExplain in Plain Language Questions with Indic Languages: Drawbacks, Affordances, and Opportunities
Background: Introductory computer science courses use ``Explain in Plain English'' (EiPE) activities to develop and assess students' code comprehension skills, but creating effective autograders for these questions is challenging and limited to English. This is a particular challenge in linguistically diverse countries like India where students may have limited proficiency in English. Methods: We evaluate the efficacy of a recently introduced approach called Code Generation Based Grading (CGBG) in enabling language agnostic ``Explain in Plain Language'' (EiPL) activities. Here students' EiPL responses generate code that is tested for functional equivalence to the original which was being described. Objectives: We initially evaluate the correctness of code generated from correct EiPL responses provided in 10 of India's most commonly spoken languages. To evaluate the effectiveness of the approach in practice, we assess student success and perceptions of EiPL questions in a NPTEL (National Programme on Technology Enhanced Learning) course. Results: We find promising results for the correctness of code generated from translations of correct EiPL responses, with most languages achieving a correctness rate of 75% or higher. However, in practice, many students preferred to respond in English due to greater familiarity with English as a technical language, difficulties writing in their native language, and perceptions of the grader being less capable of generating code from prompts in their mother tongue.