相关论文: Towards More Realistic Evaluation for Neural Test …

Statistical tests of pseudorandom number generators (PRNGs) are applicable to any type of random number generators and are indispensable for evaluation. While several practical packages for statistical tests of randomness exist, they may…

Automated unit test generation is critical for software quality but traditional structure-driven methods often lack the semantic understanding required to produce realistic inputs and oracles. Large language models (LLMs) address this…

Retriever-augmented generation (RAG) has become a widely adopted approach for enhancing the factual accuracy of large language models (LLMs). While current benchmarks evaluate the performance of RAG methods from various perspectives, they…

As Large Language Models (LLMs) transition from research environments to production deployments, evaluating their performance against strict Service Level Objectives (SLOs) has become critical. However, current evaluation methodologies…

This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer. Conventional RAG methods usually perform a single retrieval step before…

Despite impressive performance on standard benchmarks, deep neural networks are often brittle when deployed in real-world systems. Consequently, recent research has focused on testing the robustness of such models, resulting in a diverse…

Contextual Embeddings have yielded state-of-the-art results in various natural language processing tasks. However, these embeddings are constrained by models requiring large amounts of data and huge computing power. This is an issue for…

It is natural to suppose that a Large Language Model is more likely to generate correct test cases when prompted with correct code under test, compared to incorrect code under test. However, the size of this effect has never been previously…

Traditional text embedding benchmarks primarily evaluate embedding models' capabilities to capture semantic similarity. However, more advanced NLP tasks require a deeper understanding of text, such as safety and factuality. These tasks…

Software testing is a prime factor in software industry. Besides knowing the importance of testing, only limited time is allocated for teaching it. It will be more efficient if testing is taught simultaneously with programming foundations.…

Evaluation of long-form, citation-backed reports has lately received significant attention due to the wide-scale adoption of retrieval-augmented generation (RAG) systems. Core to many evaluation frameworks is the use of atomic facts, or…

Retrieval-augmented generation (RAG) is increasingly deployed in enterprise search and document-centric assistants, where responses must be grounded in long and complex source materials. In practice, verifying that generated answers…

Retrieval-augmented generation (RAG) synergizes the retrieval of pertinent data with the generative capabilities of Large Language Models (LLMs), ensuring that the generated output is not only contextually relevant but also accurate and…

Testing software is often costly due to the need of mass-producing test cases and providing a test oracle for it. This is often referred to as the oracle problem. One method that has been proposed in order to alleviate the oracle problem is…

Software engineers are increasingly adding semantic search capabilities to applications using a strategy known as Retrieval Augmented Generation (RAG). A RAG system involves finding documents that semantically match a query and then passing…

Retrieval-Augmented Generation (RAG) significantly improves the factuality of Large Language Models (LLMs), yet standard pipelines often lack mechanisms to verify inter- mediate reasoning, leaving them vulnerable to hallucinations in…

Reliably determining the performance of Retrieval-Augmented Generation (RAG) systems depends on comprehensive test questions. While a proliferation of evaluation frameworks for LLM-powered applications exists, current practices lack a…

Given an input sequence (or prefix), modern language models often assign high probabilities to output sequences that are repetitive, incoherent, or irrelevant to the prefix; as such, model-generated text also contains such artifacts. To…

Ranking is used for a wide array of problems, most notably information retrieval (search). There are a number of popular approaches to the evaluation of ranking such as Kendall's $\tau$, Average Precision, and nDCG. When dealing with…

We propose a new method to measure the task-specific accuracy of Retrieval-Augmented Large Language Models (RAG). Evaluation is performed by scoring the RAG on an automatically-generated synthetic exam composed of multiple choice questions…