Pith. sign in

REVIEW 4 cited by

Binary Code Summarization: Benchmarking ChatGPT/GPT-4 and Other Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.09601 v1 pith:23BQ5LPQ submitted 2023-12-15 cs.CR cs.CLcs.LGcs.SE

classification cs.CRcs.CLcs.LGcs.SE
keywords codebinaryllmschatgptevaluationgpt-4languagelarge
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Binary code summarization, while invaluable for understanding code semantics, is challenging due to its labor-intensive nature. This study delves into the potential of large language models (LLMs) for binary code comprehension. To this end, we present BinSum, a comprehensive benchmark and dataset of over 557K binary functions and introduce a novel method for prompt synthesis and optimization. To more accurately gauge LLM performance, we also propose a new semantic similarity metric that surpasses traditional exact-match approaches. Our extensive evaluation of prominent LLMs, including ChatGPT, GPT-4, Llama 2, and Code Llama, reveals 10 pivotal insights. This evaluation generates 4 billion inference tokens, incurred a total expense of 11,418 US dollars and 873 NVIDIA A100 GPU hours. Our findings highlight both the transformative potential of LLMs in this field and the challenges yet to be overcome.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. JsDeObsBench: Measuring and Benchmarking LLMs for JavaScript Deobfuscation

    cs.CR 2025-06 conditional novelty 7.0 of 10

    On a new execution-verifiable benchmark, LLMs simplify obfuscated JavaScript far better than rule-based tools but preserve syntax and runtime behavior much less reliably.

  2. Adapting Online Customer Reviews for Blind Users: A Case Study of Restaurant Reviews

    cs.HC 2025-06 conditional novelty 6.0 of 10

    QuickCue, an LLM-powered browser extension that reorganizes restaurant reviews into aspect-sentiment summaries, significantly improved usability and reduced workload for blind screen reader users in a 10-user study.

  3. ReCopilot: Reverse Engineering Copilot in Binary Analysis

    cs.CR 2025-05 conditional novelty 6.0 of 10

    ReCopilot is a 7B binary-analysis LLM that reports 13% higher average scores than existing tools on a new six-task benchmark, but the benchmark and artifacts are not released.

  4. Idioms: Neural Decompilation With Joint Code and Type Definition Prediction

    cs.SE 2025-02 conditional novelty 6.0 of 10

    Finetuned LLMs that jointly generate decompiled C code and user-defined type definitions outperform prior neural decompilers on ExeBench and the new Realtype dataset.

Pith tools