Related papers: TestDecision: Sequential Test Suite Generation via…

While model serving has unlocked unprecedented capabilities, the high cost of serving large-scale models continues to be a significant barrier to widespread accessibility and rapid innovation. Compiler optimizations have long driven…

Decoding strategies largely determine the quality of Large Language Model (LLM) outputs, yet widely used heuristics such as greedy or fixed temperature/top-p decoding are static and often task-agnostic, leading to suboptimal or inconsistent…

New Large Language Models (LLMs) become available every few weeks, and modern application developers confronted with the unenviable task of having to decide if they should switch to a new model. While human evaluation remains the gold…

The quality of meeting summaries generated by natural language generation (NLG) systems is hard to measure automatically. Established metrics such as ROUGE and BERTScore have a relatively low correlation with human judgments and fail to…

Unit tests (UTs) play an instrumental role in assessing code correctness as well as providing feedback to large language models (LLMs), motivating automated test generation. However, we uncover a trade-off between generating unit test…

This paper describes a rapid feasibility study of using GPT-4, a large language model (LLM), to (semi)automate data extraction in systematic reviews. Despite the recent surge of interest in LLMs there is still a lack of understanding of how…

The evaluation of code-generating Large Language Models (LLMs) is fundamentally constrained by two intertwined challenges: a reliance on static, easily contaminated problem sources and the use of superficial, low-rigor testing. This paper…

With the wide adoption of language models for IR -- and specifically RAG systems -- the latency of the underlying LLM becomes a crucial bottleneck, since the long contexts of retrieved passages lead large prompts and therefore, compute…

The process of testing any software system is an enormous task which is time consuming and costly. The time and required effort to do sufficient testing grow, as the size and complexity of the software grows, which may cause overrun of the…

Large Language Models (LLMs) are increasingly applied to automated software testing, yet their ability to generalize beyond memorized patterns and reason about natural language bug reports remains unclear. We present a systematic evaluation…

This paper presents a simple, effective, and cost-efficient strategy to improve LLM performance by scaling test-time compute. Our strategy builds upon the repeated-sampling-then-voting framework, with a novel twist: incorporating multiple…

Test-time compute can be scaled both sequentially and in parallel. Sequential scaling involves lengthening the generation process, while parallel scaling involves verifying and selecting among multiple candidate outputs. Combining these two…

Large Language Models (LLMs) employ three popular training approaches: Masked Language Models (MLM), Causal Language Models (CLM), and Sequence-to-Sequence Models (seq2seq). However, each approach has its strengths and limitations, and…

Traditional approaches to test case generation often involve manual effort and incur significant computational overhead. Additionally, these approaches are not scalable, and hence, unsuitable for complex software systems. Recently, Large…

Large language models (LLMs) have recently been employed as agents to solve sequential decision-making tasks such as Bayesian optimization and multi-armed bandits (MAB). These works usually adopt an LLM for sequential action selection by…

Background: Software systems powered by large language models are becoming a routine part of everyday technologies, supporting applications across a wide range of domains. In software engineering, many studies have focused on how LLMs…

The integration of Formal Verification tools with Large Language Models (LLMs) offers a path to scale software verification beyond manual workflows. However, current methods remain unreliable: without a solid theoretical footing, the…

Large Language Models (LLMs) have revolutionized various domains but encounter substantial challenges in tackling optimization modeling tasks for Operations Research (OR), particularly when dealing with complex problem. In this work, we…

Recent advances in test-time scaling have shown promising results in improving Large Language Model (LLM) performance through strategic computation allocation during inference. While this approach has demonstrated strong improvements in…

Test-time scaling (TTS) has gained widespread attention for enhancing LLM reasoning. Existing approaches such as Best-of-N and majority voting are limited as their performance depends on the quality of candidate responses, making them…