SONAR: Task-Aware Code Summary Evaluation for LLM Consumers Without References

• URL: http://arxiv.org/abs/2608.04195v1
• Date: Tue, 04 Aug 2026 19:54:45 GMT
• Title: SONAR: Task-Aware Code Summary Evaluation for LLM Consumers Without References
• Abstract summary: Source code summaries have traditionally been evaluated from a human developer's perspective.<n>But this overlooks a growing reality: LLM-based tools and agents increasingly consume code summaries as inputs for software engineering tasks.<n>We propose SONAR, a reference-free framework that evaluates source code summaries along four dimensions.
• Score: 15.211628096103473
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Source code summaries have traditionally been evaluated from a human developer's perspective, with quality determined by how closely they resemble developer-written references and how well they align with human preferences. But this overlooks a growing reality: LLM-based tools and agents increasingly consume code summaries as inputs for software engineering (SE) tasks, and what makes a summary useful for a consuming agent on a task remains largely unexplored. To bridge this gap, we propose SONAR, a reference-free framework that evaluates source code summaries along four dimensions: Correctness, Abstraction, Conciseness, and Fluency. Rather than optimizing for a pre-written "gold standard", SONAR introduces a novel code regeneration-based approach that uses a summary to regenerate code and leverages that reconstruction as a quality signal of the summary. This provides an empirical grounding that requires neither a reference summary nor the subjective judgment of humans or LLMs. We evaluate SONAR's dimensions on their ability to influence LLM performance across four downstream SE tasks. We find that Correctness, followed by Abstraction, significantly correlates with LLM performance, with correlations up to 14X higher than the best baseline. Conciseness and Fluency, though widely valued by human developers, remain mostly insignificant to an LLM consumer, suggesting that what makes a summary useful is task- and consumer-dependent. Through a large-scale evaluation of 11 popular LLMs using SONAR, we further identify the strengths and weaknesses of different models across each quality dimension, while offering insights to facilitate future research on task-aware summarization.

Related papers

• RAVEL: Reasoning Agents for Validating and Evaluating LLM Text Synthesis [78.32151470154422]
  We introduce RAVEL, an agentic framework that enables the testers to autonomously plan and execute typical synthesis operations.<n>We present C3EBench, a benchmark comprising 1,258 samples derived from professional human writings.<n>By augmenting RAVEL with SOTA LLMs as operators, we find that such agentic text synthesis is dominated by the LLM's reasoning capability.
  arXiv  Detail & Related papers  (2026-02-28T14:47:34Z)
• DEEPQUESTION: Systematic Generation of Real-World Challenges for Evaluating LLMs Performance [3.9770095824794516]
  We introduce DeepQuestion, a scalable automated framework that augments existing datasets based on Bloom's taxonomy.<n>We show substantial performance drops (even up to 70% accuracy loss) on higher-order tasks, underscoring persistent gaps in deep reasoning.
  arXiv  Detail & Related papers  (2025-05-30T12:39:42Z)
• IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis [60.32962597618861]
  IDA-Bench is a novel benchmark evaluating large language models in multi-round interactive scenarios.<n>Agent performance is judged by comparing its final numerical output to the human-derived baseline.<n>Even state-of-the-art coding agents (like Claude-3.7-thinking) succeed on 50% of the tasks, highlighting limitations not evident in single-turn tests.
  arXiv  Detail & Related papers  (2025-05-23T09:37:52Z)
• Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision [50.45597801390757]
  Instruct-LF is a goal-oriented latent factor discovery system.<n>It integrates instruction-following ability with statistical models to handle noisy datasets.
  arXiv  Detail & Related papers  (2025-02-21T02:03:08Z)
• To Err Is Human; To Annotate, SILICON? Reducing Measurement Error in LLM Annotation [11.470318058523466]
  Large Language Models (LLMs) promise a cost-effective scalable alternative to human annotation.<n>We develop the SILICON methodology to systematically reduce measurement error from LLM annotation.<n>Our evidence indicates that reducing each error source is necessary, and that SILICON supports rigorous annotation in management research.
  arXiv  Detail & Related papers  (2024-12-19T02:21:41Z)
• UserSumBench: A Benchmark Framework for Evaluating User Summarization Approaches [25.133460380551327]
  Large language models (LLMs) have shown remarkable capabilities in generating user summaries from a long list of raw user activity data. These summaries capture essential user information such as preferences and interests, and are invaluable for personalization applications. However, the development of new summarization techniques is hindered by the lack of ground-truth labels, the inherent subjectivity of user summaries, and human evaluation.
  arXiv  Detail & Related papers  (2024-08-30T01:56:57Z)
• Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models [43.56644186785491]
  This paper proposes the RACE benchmark, which comprehensively evaluates the quality of code generated by large language models. We analyze 28 representative LLMs based on RACE and find that current correctness-centric benchmarks fail to capture the multifaceted requirements of code in real-world scenarios.
  arXiv  Detail & Related papers  (2024-07-16T08:08:48Z)
• RepEval: Effective Text Evaluation with LLM Representation [55.26340302485898]
  RepEval is a metric that leverages the projection of Large Language Models (LLMs) representations for evaluation. Our work underscores the richness of information regarding text quality embedded within LLM representations, offering insights for the development of new metrics.
  arXiv  Detail & Related papers  (2024-04-30T13:50:55Z)
• Summarization is (Almost) Dead [49.360752383801305]
  We develop new datasets and conduct human evaluation experiments to evaluate the zero-shot generation capability of large language models (LLMs) Our findings indicate a clear preference among human evaluators for LLM-generated summaries over human-written summaries and summaries generated by fine-tuned models.
  arXiv  Detail & Related papers  (2023-09-18T08:13:01Z)
• On Learning to Summarize with Large Language Models as References [101.79795027550959]
  Large language models (LLMs) are favored by human annotators over the original reference summaries in commonly used summarization datasets. We study an LLM-as-reference learning setting for smaller text summarization models to investigate whether their performance can be substantially improved.
  arXiv  Detail & Related papers  (2023-05-23T16:56:04Z)

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.