On Explaining (Large) Language Models For Code Using Global Code-Based Explanations

• URL: http://arxiv.org/abs/2503.16771v1
• Date: Fri, 21 Mar 2025 01:00:45 GMT
• Title: On Explaining (Large) Language Models For Code Using Global Code-Based Explanations
• Authors: David N. Palacio, Dipin Khati, Daniel Rodriguez-Cardenas, Alejandro Velasco, Denys Poshyvanyk,
• Abstract summary: Language Models for Code (LLM4Code) have significantly changed the landscape of software engineering (SE)<n>We introduce code rationales (Code$Q$), a technique with rigorous mathematical underpinning, to identify subsets of tokens that can explain individual code predictions.<n>Our evaluation demonstrates that Code$Q$ is a powerful interpretability method to explain how (less) meaningful input concepts (i.e., natural language particle at') highly impact output generation.
• Score: 45.126233498200534
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: In recent years, Language Models for Code (LLM4Code) have significantly changed the landscape of software engineering (SE) on downstream tasks, such as code generation, by making software development more efficient. Therefore, a growing interest has emerged in further evaluating these Language Models to homogenize the quality assessment of generated code. As the current evaluation process can significantly overreact on accuracy-based metrics, practitioners often seek methods to interpret LLM4Code outputs beyond canonical benchmarks. While the majority of research reports on code generation effectiveness in terms of expected ground truth, scant attention has been paid to LLMs' explanations. In essence, the decision-making process to generate code is hard to interpret. To bridge this evaluation gap, we introduce code rationales (Code$Q$), a technique with rigorous mathematical underpinning, to identify subsets of tokens that can explain individual code predictions. We conducted a thorough Exploratory Analysis to demonstrate the method's applicability and a User Study to understand the usability of code-based explanations. Our evaluation demonstrates that Code$Q$ is a powerful interpretability method to explain how (less) meaningful input concepts (i.e., natural language particle `at') highly impact output generation. Moreover, participants of this study highlighted Code$Q$'s ability to show a causal relationship between the input and output of the model with readable and informative explanations on code completion and test generation tasks. Additionally, Code$Q$ also helps to uncover model rationale, facilitating comparison with a human rationale to promote a fair level of trust and distrust in the model.

Related papers

• SURGE: On the Potential of Large Language Models as General-Purpose Surrogate Code Executors [0.0]
  Large language models (LLMs) have demonstrated remarkable capabilities in code-related tasks.<n>Given LLMs' ability to understand and process diverse programs, they present a promising direction for building general-purpose surrogate models.<n>We introduce SURGE, a benchmark with $1160$ problems covering $8$ key aspects.<n>Through empirical analysis of $21$ open-source and proprietary LLMs, we examine scaling laws, data efficiency, and predictive accuracy.
  arXiv  Detail & Related papers  (2025-02-16T15:38:19Z)
• A Tool for In-depth Analysis of Code Execution Reasoning of Large Language Models [1.644043499620662]
  This paper introduces ExeRScope, a series of tools to analyze the result of code execution reasoning frameworks.<n>Analysis can be generalized to code with similar properties without the urgent need to design more benchmarks.
  arXiv  Detail & Related papers  (2025-01-30T16:56:08Z)
• Correctness Assessment of Code Generated by Large Language Models Using Internal Representations [4.32362000083889]
  We introduce OPENIA, a novel framework to assess the correctness of code generated by Large Language Models (LLMs)<n>Our empirical analysis reveals that these internal representations encode latent information, which strongly correlates with the correctness of the generated code.<n> OPENIA consistently outperforms baseline models, achieving higher accuracy, precision, recall, and F1-Scores with up to a 2X improvement in standalone code generation.
  arXiv  Detail & Related papers  (2025-01-22T15:04:13Z)
• Is Functional Correctness Enough to Evaluate Code Language Models? Exploring Diversity of Generated Codes [17.95094238686012]
  Language models (LMs) have exhibited impressive abilities in generating codes from natural language requirements. We highlight the diversity of code generated by LMs as a critical criterion for evaluating their code generation capabilities. We propose a systematic approach to evaluate the diversity of generated code, utilizing various metrics for inter-code similarity as well as functional correctness.
  arXiv  Detail & Related papers  (2024-08-24T07:40:22Z)
• Comments as Natural Logic Pivots: Improve Code Generation via Comment Perspective [85.48043537327258]
  We propose MANGO (comMents As Natural loGic pivOts), including a comment contrastive training strategy and a corresponding logical comment decoding strategy. Results indicate that MANGO significantly improves the code pass rate based on the strong baselines. The robustness of the logical comment decoding strategy is notably higher than the Chain-of-thoughts prompting.
  arXiv  Detail & Related papers  (2024-04-11T08:30:46Z)
• Reasoning Runtime Behavior of a Program with LLM: How Far Are We? [25.451857140926943]
  Large language models for code (i.e., code LLMs) have shown strong code understanding and generation capabilities. Code reasoning is one of the most essential abilities of code LLMs. We propose a framework, namely REval, for evaluating code reasoning abilities and consistency of code LLMs with program execution.
  arXiv  Detail & Related papers  (2024-03-25T05:37:16Z)
• LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models [63.14196038655506]
  We introduce LogicAsker, a novel approach for evaluating and enhancing the logical reasoning capabilities of large language models (LLMs) Our methodology reveals significant gaps in LLMs' learning of logical rules, with identified reasoning failures ranging from 29% to 90% across different models. We leverage these findings to construct targeted demonstration examples and fine-tune data, notably enhancing logical reasoning in models like GPT-4o by up to 5%.
  arXiv  Detail & Related papers  (2024-01-01T13:53:53Z)
• Understanding Code Semantics: An Evaluation of Transformer Models in Summarization [0.0]
  We evaluate the efficacy of code summarization by altering function and variable names. We introduce adversaries like dead code and commented code across three programming languages.
  arXiv  Detail & Related papers  (2023-10-25T02:41:50Z)
• Benchmarking and Explaining Large Language Model-based Code Generation: A Causality-Centric Approach [12.214585409361126]
  Large language models (LLMs)- based code generation is a complex and powerful black-box model. We propose a novel causal graph-based representation of the prompt and the generated code. We illustrate the insights that our framework can provide by studying over 3 popular LLMs with over 12 prompt adjustment strategies.
  arXiv  Detail & Related papers  (2023-10-10T14:56:26Z)
• L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models [102.00201523306986]
  We present L2CEval, a systematic evaluation of the language-to-code generation capabilities of large language models (LLMs) We analyze the factors that potentially affect their performance, such as model size, pretraining data, instruction tuning, and different prompting methods. In addition to assessing model performance, we measure confidence calibration for the models and conduct human evaluations of the output programs.
  arXiv  Detail & Related papers  (2023-09-29T17:57:00Z)
• Evaluating and Explaining Large Language Models for Code Using Syntactic Structures [74.93762031957883]
  This paper introduces ASTxplainer, an explainability method specific to Large Language Models for code. At its core, ASTxplainer provides an automated method for aligning token predictions with AST nodes. We perform an empirical evaluation on 12 popular LLMs for code using a curated dataset of the most popular GitHub projects.
  arXiv  Detail & Related papers  (2023-08-07T18:50:57Z)
• A Transformer-based Approach for Source Code Summarization [86.08359401867577]
  We learn code representation for summarization by modeling the pairwise relationship between code tokens. We show that despite the approach is simple, it outperforms the state-of-the-art techniques by a significant margin.
  arXiv  Detail & Related papers  (2020-05-01T23:29:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.