計算機構論 II （2025年度Sセメスター）
授業の形式と目的
本講義では，プログラミング言語・プログラミングににまつわる最近のトピックスについて輪講形式で学びます．2025年度は「大規模言語モデルとプログラミング」をテーマとし，ソフトウェア科学・工学の広範な分野にまたがる下記の文献リストから，各人が興味があるものを選び輪講形式で発表します（文献リストは変更される可能性があります）．
初回にガイダンスを行い，各人の担当部分の割当てを決めます． なお、2回目は森畑が文献1を紹介する予定です．
基本情報
担当教員：森畑明昌（総合文化研究科）　morihata_AT_graco.c.u-tokyo.ac.jp
曜限：月曜3限（13:15-14:45）
オンライン開講の予定です．
※履修希望者は4/16までに以下のフォームに記入・提出してください．
履修登録フォーム
授業計画（敬称略）
文献リスト
  1. Large Language Models for Software Engineering: A Systematic Literature Review.
    ACM Transactions on Software Engineering and Methodology, Volume 33, Issue 8, No. 220, Pages 1 - 79, 2024.
  2. LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarks. IEEE Symposium on Security and Privacy, 2024.
  3. PromSec: Prompt Optimization for Secure Generation of Functional Source Code with Large Language Models (LLMs). ACM Conference on Computer and Communications Security, 2024.
  4. ReSym: Harnessing LLMs to Recover Variable and Data Structure Symbols from Stripped Binaries. ACM Conference on Computer and Communications Security, 2024.
  5. ProphetFuzz: Fully Automated Prediction and Fuzzing of High-Risk Option Combinations with Only Documentation via Large Language Model. ACM Conference on Computer and Communications Security, 2024.
  6. Exploiting Code Symmetries for Learning Program Semantics. International Conference on Machine Learnig, 2024.
  7. Emergent Representations of Program Semantics in Language Models Trained on Programs. International Conference on Machine Learnig, 2024.
  8. ReGAL: Refactoring Programs to Discover Generalizable Abstractions. International Conference on Machine Learnig, 2024.
  9. Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates. International Conference on Machine Learnig, 2024.
  10. Make LLM a Testing Expert: Bringing Human-like Interaction to Mobile GUI Testing via Functionality-aware Decisions. IEEE/ACM International Conference on Software Engineering, 2024.
  11. Using an LLM to Help With Code Understanding. IEEE/ACM International Conference on Software Engineering, 2024.
  12. UniLog: Automatic Logging via LLM and In-Context Learning. IEEE/ACM International Conference on Software Engineering, 2024.
  13. Large Language Models for Test-Free Fault Localization. IEEE/ACM International Conference on Software Engineering, 2024.
  14. Software Engineering Education Must Adapt and Evolve for an LLM Environment. ACM Technical Symposium on Computer Science Education, 2024.
  15. A Benchmark for Testing the Capabilities of LLMs in Assessing the Quality of Multiple-choice Questions in Introductory Programming Education. ACM Technical Symposium on Computer Science Education, 2024.
  16. Generative AI in Introductory Programming Instruction: Examining the Assistance Dilemma with LLM-Based Code Generators. ACM Technical Symposium on Computer Science Education, 2024.
  17. Integrating Natural Language Prompting Tasks in Introductory Programming Courses. ACM Technical Symposium on Computer Science Education, 2024.
Akimasa Morihata. Feb., 2025