Ambiguity Resolution with Human Feedback for Code Writing Tasks

Aditey Nandan, Viraj Kumar
8/18/2025
cs.SEcs.AI

No official code found. Best implementation: Nandan-Aditey/ARHF (1 star, MIT, last commit 2025-09-26). 1 more below.

Abstract

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.

View on arXivView PDF

Code Implementations(2)

Nandan-Aditey/ARHFCommunity73%
MIT

Repository containing code for ARHF: Ambiguity Resolution with Human Feedback for Code Writing Tasks

10CSS, HTMLAug 26, 20251 years agoMIT
Nandan-Aditey/ARHF-ResourcesCommunity66%
MIT

This repository contains the prompts, problems, and figures related to the paper: Ambiguity Resolution with Human Feedback for Code Writing Tasks

00PythonAug 16, 20251 years agoMIT

Similar Papers

Curiosity by Design: An LLM-based Coding Assistant Asking Clarification Questions

82% match2025

EduBot -- Can LLMs Solve Personalized Learning and Programming Assignments?

81% match2025

Interactions with Prompt Problems: A New Way to Teach Programming with Large Language Models

81% match2024

Exploring the Design Space of Cognitive Engagement Techniques with AI-Generated Code for Enhanced Learning

80% match2024

One Step at a Time: Combining LLMs and Static Analysis to Generate Next-Step Hints for Programming Tasks

80% match2024

Assessing AI Detectors in Identifying AI-Generated Code: Implications for Education

80% match2024

Cite this paper

@article{nandan2025ambiguity,
  title  = {Ambiguity Resolution with Human Feedback for Code Writing Tasks},
  author = {Aditey Nandan and Viraj Kumar},
  year   = {2025},
  eprint = {2508.14114},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2508.14114v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2508.14114.svg)](https://codeofpaper.com/paper/2508.14114)

Discussion