相关论文: Majority Voting for Code Generation

Test-time scaling has emerged as a promising approach for improving code generation by exploring large solution spaces at inference time. However, existing methods often rely on public test cases that are unavailable in practice, or require…

LLM-based RTL generation is an interesting research direction, as it holds the potential to liberate the least automated stage in the current chip design. However, due to the substantial semantic gap between high-level specifications and…

Automating hardware design could obviate a significant amount of human error from the engineering process and lead to fewer errors. Verilog is a popular hardware description language to model and design digital systems, thus generating…

To enhance the reasoning capabilities of Large Language Models (LLMs) without high costs of training, nor extensive test-time sampling, we introduce Verification-First (VF), a strategy that prompts models to verify a provided candidate…

Recent advances such as self-consistency and test-time reinforcement learning (TTRL) improve the reliability of large language models (LLMs) without additional supervision, yet their underlying mechanisms and statistical guarantees remain…

The dominant approach to generating from language models subject to some constraint is locally constrained decoding (LCD), incrementally sampling tokens at each time step such that the constraint is never violated. Typically, this is…

This paper explores a novel method for enhancing binary classification models that assess code comment quality, leveraging Generative Artificial Intelligence to elevate model performance. By integrating 1,437 newly generated code-comment…

The rise of Large Language Models (LLMs) has boosted the use of Few-Shot Learning (FSL) methods in natural language processing, achieving acceptable performance even when working with limited training data. The goal of FSL is to effectively…

Large Language Models (LLMs), particularly Code LLMs, have demonstrated impressive performance in code generation. Current research primarily focuses on the correctness of generated code, while efficiency remains less explored. Recent works…

Generations from large language models (LLMs) can be improved by sampling and scoring multiple solutions to select a final answer. Current "sample and select" methods such as self-consistency (SC) rely on majority voting to score answers.…

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…

Large Language Models (LLMs) are used for many tasks, including those related to coding. An important aspect of being able to utilize LLMs is the ability to assess their fitness for specific usages. The common practice is to evaluate LLMs…

Majority voting has proven effective for close-ended question answering by aggregating parallel reasoning traces. However, it is not directly applicable to open-ended reasoning, such as code generation and web-based deep research, where a…

Weighted voting is a conventional approach to improving the performance of replicated systems based on commonly-used majority quorum systems in heterogeneous environments. In long-lived systems, a weight reassignment protocol is required to…

Quality assurance remains a key topic in human computation research. Prior work indicates that majority voting is effective for low difficulty tasks, but has limitations for harder tasks. This paper explores two methods of addressing this…

Self-Consistency samples diverse reasoning chains with answers and chooses the final answer by majority voting. It is based on forward reasoning and cannot further improve performance by sampling more reasoning chains when saturated. To…

Large Vision-Language Models (LVLMs) have achieved remarkable success, yet their significant computational demands hinder practical deployment. While efforts to improve LVLM efficiency are growing, existing methods lack comprehensive…

Generating simulations to train intelligent agents in game-playing and robotics from natural language input, from user input or task documentation, remains an open-ended challenge. Existing approaches focus on parts of this challenge, such…

Large Language Models (LLMs) are widely adopted for assisting in software development tasks, yet their performance evaluations have narrowly focused on the functional correctness of generated code. Human programmers, however, require…

Generating and voting multiple answers is an effective method to mitigate reasoning inconsistencies of large language models (LLMs). Prior works have shown that multiple reasoning formats outperform a single format when generating multiple…