English
Related papers

Related papers: Exploring Language Model's Code Generation Ability…

200 papers

We investigate how code obfuscation influences human understanding of programs through an output-prediction task. To study this effect, we construct multiple levels of obfuscation, ranging from unobfuscated code to transformations involving…

Software Engineering · Computer Science 2026-03-10 Anh H. N. Nguyen , Jack Le , Ilse Lahnstein Coronado , Tien N. Nguyen

Large language models are highly capable of answering difficult questions by retrieving, recombining, and attending to information in long contexts. For agentic tasks, an additional capability is required: the preservation of an exact state…

Computation and Language · Computer Science 2026-05-19 Tianxiang Dai , Jonathan Fan

Humans do not just find mistakes after the fact -- we often catch them mid-stream because 'reflection' is tied to the goal and its constraints. Today's large language models produce reasoning tokens and 'reflective' text, but is it…

Artificial Intelligence · Computer Science 2025-10-24 Sion Weatherhead , Flora Salim , Aaron Belbasis

Recent work studies the cognitive capabilities of language models through psychological tests designed for humans. While these studies are helpful for understanding the general capabilities of these models, there is no guarantee that a…

Computation and Language · Computer Science 2023-05-30 Lingjun Zhao , Khanh Nguyen , Hal Daumé

Subword tokenization introduces a computational layer in language models where many distinct token sequences decode to the same surface form and preserve meaning, yet induce different internal computations. Despite this non-uniqueness,…

Computation and Language · Computer Science 2026-01-14 Adrian Cosma , Stefan Ruseti , Emilian Radoi , Mihai Dascalu

Recent works have successfully applied Large Language Models (LLMs) to function modeling tasks. However, the reasons behind this success remain unclear. In this work, we propose a new evaluation framework to comprehensively assess LLMs'…

Machine Learning · Computer Science 2024-10-08 Shoaib Ahmed Siddiqui , Yanzhi Chen , Juyeon Heo , Menglin Xia , Adrian Weller

The prominent large language models (LLMs) of today differ from past language models not only in size, but also in the fact that they are trained on a combination of natural language and formal language (code). As a medium between humans…

Computation and Language · Computer Science 2024-01-09 Ke Yang , Jiateng Liu , John Wu , Chaoqi Yang , Yi R. Fung , Sha Li , Zixuan Huang , Xu Cao , Xingyao Wang , Yiquan Wang , Heng Ji , Chengxiang Zhai

The impressive performance of recent language models across a wide range of tasks suggests that they possess a degree of abstract reasoning skills. Are these skills general and transferable, or specialized to specific tasks seen during…

Computation and Language · Computer Science 2024-04-01 Zhaofeng Wu , Linlu Qiu , Alexis Ross , Ekin Akyürek , Boyuan Chen , Bailin Wang , Najoung Kim , Jacob Andreas , Yoon Kim

Large language models have shown good performances in generating code to meet human requirements. However, human requirements expressed in natural languages can be vague, incomplete, and ambiguous, leading large language models to…

Software Engineering · Computer Science 2023-11-02 Zejun Wang , Jia Li , Ge Li , Zhi Jin

Recent advancements in large language models (LLMs) have significantly enhanced code generation from natural language prompts. The HumanEval Benchmark, developed by OpenAI, remains the most widely used code generation benchmark. However,…

Computation and Language · Computer Science 2025-05-19 Nishat Raihan , Antonios Anastasopoulos , Marcos Zampieri

Behavioural testing -- verifying system capabilities by validating human-designed input-output pairs -- is an alternative evaluation method of natural language processing systems proposed to address the shortcomings of the standard…

Computation and Language · Computer Science 2022-07-05 Pedro Henrique Luz de Araujo , Benjamin Roth

Large language models (LLMs) struggle to consistently generate UI code that compiles and produces visually relevant designs. Existing approaches to improve generation rely on expensive human feedback or distilling a proprietary model. In…

Computation and Language · Computer Science 2024-06-13 Jason Wu , Eldon Schoop , Alan Leung , Titus Barik , Jeffrey P. Bigham , Jeffrey Nichols

Recent development of large language models (LLMs) for code like CodeX and CodeT5+ demonstrates tremendous promise in achieving code intelligence. Their ability of synthesizing code that completes a program for performing a pre-defined task…

Computation and Language · Computer Science 2023-10-10 Weimin Xiong , Yiwen Guo , Hao Chen

Language agents increasingly improve by reusing \emph{skills} -- structured procedural artifacts distilled from past experience. In particular, \emph{domain-level} and \emph{model-generated} skills are especially promising. They offer fast…

In recent years, Large Language Models have garnered significant attention for their strong performance in various natural language tasks, such as machine translation and question answering. These models demonstrate an impressive ability to…

Computation and Language · Computer Science 2025-02-21 Qibang Liu , Wenzhe Wang , Jeffrey Willard

Complex, multi-task problems have proven to be difficult to solve efficiently in a sparse-reward reinforcement learning setting. In order to be sample efficient, multi-task learning requires reuse and sharing of low-level policies. To…

Machine Learning · Computer Science 2021-09-28 Valerie Chen , Abhinav Gupta , Kenneth Marino

Large Language Models (LLMs) have demonstrated unprecedented capability in code generation. However, LLM-generated code is still plagued with a wide range of functional errors, especially for complex programming tasks that LLMs have not…

Software Engineering · Computer Science 2025-05-13 Yifeng Di , Tianyi Zhang

This work introduces self-infilling code generation, a general framework that incorporates infilling operations into auto-regressive decoding. Our approach capitalizes on the observation that recent infilling-capable code language models…

Programming Languages · Computer Science 2024-05-28 Lin Zheng , Jianbo Yuan , Zhi Zhang , Hongxia Yang , Lingpeng Kong

Large language models (LLMs) have shown impressive capabilities across a wide range of language tasks. However, their reasoning process is primarily guided by statistical patterns in training data, which limits their ability to handle novel…

Artificial Intelligence · Computer Science 2025-08-21 Hong Su

We propose iteratively prompting a large language model to self-correct a translation, with inspiration from their strong language understanding and translation capability as well as a human-like translation approach. Interestingly,…

Computation and Language · Computer Science 2024-05-03 Pinzhen Chen , Zhicheng Guo , Barry Haddow , Kenneth Heafield