Saved in:
Bibliographic Details
Main Authors: Shbita, Basel, Gentile, Anna Lisa, Zhang, Bing, An, Sungeun, Thakur, Shailja, Asthana, Shubhi, Zhou, Yi, Surendran, Saptha, Ahmed, Farhan, Kulkarni, Rohan, Ong, Yuya Jeremy, DeLuca, Chad, Patel, Hima
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.23027
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915956289175552
author Shbita, Basel
Gentile, Anna Lisa
Zhang, Bing
An, Sungeun
Thakur, Shailja
Asthana, Shubhi
Zhou, Yi
Surendran, Saptha
Ahmed, Farhan
Kulkarni, Rohan
Ong, Yuya Jeremy
DeLuca, Chad
Patel, Hima
author_facet Shbita, Basel
Gentile, Anna Lisa
Zhang, Bing
An, Sungeun
Thakur, Shailja
Asthana, Shubhi
Zhou, Yi
Surendran, Saptha
Ahmed, Farhan
Kulkarni, Rohan
Ong, Yuya Jeremy
DeLuca, Chad
Patel, Hima
contents Large language models (LLMs) have become central to modern AI workflows, powering applications from open-ended text generation to complex agent-based reasoning. However, debugging these models remains a persistent challenge due to their opaque and probabilistic nature and the difficulty of diagnosing errors across diverse tasks and settings. This paper introduces a systematic approach for LLM debugging that treats models as observable systems, providing structured, model-agnostic methods from issue detection to model refinement. By unifying evaluation, interpretability, and error-analysis practices, our approach enables practitioners to iteratively diagnose model weaknesses, refine prompts and model parameters, and adapt data for fine-tuning or assessment, while remaining effective in contexts where standardized benchmarks and evaluation criteria are lacking. We argue that such a structured methodology not only accelerates troubleshooting but also fosters reproducibility, transparency, and scalability in the deployment of LLM-based systems.
format Preprint
id arxiv_https___arxiv_org_abs_2604_23027
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Systematic Approach for Large Language Models Debugging
Shbita, Basel
Gentile, Anna Lisa
Zhang, Bing
An, Sungeun
Thakur, Shailja
Asthana, Shubhi
Zhou, Yi
Surendran, Saptha
Ahmed, Farhan
Kulkarni, Rohan
Ong, Yuya Jeremy
DeLuca, Chad
Patel, Hima
Artificial Intelligence
Large language models (LLMs) have become central to modern AI workflows, powering applications from open-ended text generation to complex agent-based reasoning. However, debugging these models remains a persistent challenge due to their opaque and probabilistic nature and the difficulty of diagnosing errors across diverse tasks and settings. This paper introduces a systematic approach for LLM debugging that treats models as observable systems, providing structured, model-agnostic methods from issue detection to model refinement. By unifying evaluation, interpretability, and error-analysis practices, our approach enables practitioners to iteratively diagnose model weaknesses, refine prompts and model parameters, and adapt data for fine-tuning or assessment, while remaining effective in contexts where standardized benchmarks and evaluation criteria are lacking. We argue that such a structured methodology not only accelerates troubleshooting but also fosters reproducibility, transparency, and scalability in the deployment of LLM-based systems.
title A Systematic Approach for Large Language Models Debugging
topic Artificial Intelligence
url https://arxiv.org/abs/2604.23027