Better Context Makes Better Code Language Models: A Case Study on Function Call Argument Completion

2023-06-01 · Hengzhi Pei, Jinman Zhao, Leonard Lausen, Sheng Zha, George Karypis

Pretrained code language models have enabled great progress towards program synthesis. However, common approaches only consider in-file local context and thus miss information and constraints imposed by other parts of the codebase and its external dependencies. Existing code completion benchmarks also lack such context. To resolve these restrictions we curate a new dataset of permissively licensed Python packages that includes full projects and their dependencies and provide tools to extract non-local information with the help of program analyzers. We then focus on the task of function call argument completion which requires predicting the arguments to function calls. We show that existing code completion models do not yield good results on our completion task. To better solve this task, we query a program analyzer for information relevant to a given function call, and consider ways to provide the analyzer results to different code completion models during inference and training. Our experiments show that providing access to the function implementation and function usages greatly improves the argument completion performance. Our ablation study provides further insights on how different types of information available from the program analyzer and different ways of incorporating the information affect the model performance.

📄 PDF Abstract BibTeX arXiv:2306.00381

Code (0)

등록된 구현이 없습니다.

Tasks

Code Completion Program Synthesis

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Relative Positioning Based Code Chunking Method For Rich Context Retrieval In Repository Level Code Completion Task With Code Language Model

2025-10-07 · Imranur Rahman, Md Rayhanur Rahman arxiv

Code completion can help developers improve efficiency and ease the development lifecycle. Although code completion is available in modern integrated development environments (IDEs), research lacks in determining what ma…

Semantic Similarity Code Completion

Linguistic Knowledge and Transferability of Contextual Representations

2019-03-21 · NAACL 2019 6 · Nelson F. Liu, Matt Gardner, Yonatan Belinkov, Matthew E. Peters 외

Contextual word representations derived from large-scale neural language models are successful across a diverse set of NLP tasks, suggesting that they encode useful and transferable features of language. To shed light on…

Language Modeling Language Modelling

Supervised Knowledge Makes Large Language Models Better In-context Learners

2023-12-26 · Linyi Yang, Shuibai Zhang, Zhuohao Yu, Guangsheng Bao 외

Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The recent progress in large-scale generative models has further expanded their use in real-world language applicati…

In-Context Learning Natural Language Understanding Prompt Engineering Question Answering

Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning

2026-03-10 · Tiehua Mei, Minxuan Lv, Leiyu Pan, Zhenpeng Su 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that arrive at correct answers by chance. …

Reinforcement Learning Mathematical Reasoning

Contextual Density Ratio for Language Model Biasing of Sequence to Sequence ASR Systems

2022-06-29 · Jesús Andrés-Ferrer, Dario Albesano, Puming Zhan, Paul Vozila

End-2-end (E2E) models have become increasingly popular in some ASR tasks because of their performance and advantages. These E2E models directly approximate the posterior distribution of tokens given the acoustic inputs.…