Related papers: Quantifying and Improving the Robustness of Retrie…

Large language models (LLMs) inevitably exhibit hallucinations since the accuracy of generated texts cannot be secured solely by the parametric knowledge they encapsulate. Although retrieval-augmented generation (RAG) is a practicable…

Retrieval-Augmented Generation (RAG) systems have emerged as a promising solution to mitigate LLM hallucinations and enhance their performance in knowledge-intensive domains. However, these systems are vulnerable to adversarial poisoning…

Automatic Speech Recognition (ASR) systems must be robust to the myriad types of noises present in real-world environments including environmental noise, room impulse response, special effects as well as attacks by malicious actors…

Reproducibility is a cornerstone of scientific progress, yet its state in large language model (LLM)-based software engineering (SE) research remains poorly understood. This paper presents the first large-scale, empirical study of…

The indexing-retrieval-generation paradigm of retrieval-augmented generation (RAG) has been highly successful in solving knowledge-intensive tasks by integrating external knowledge into large language models (LLMs). However, the…

Reasoning has emerged as the next major frontier for language models (LMs), with rapid advances from both academic and industrial labs. However, this progress often outpaces methodological rigor, with many evaluations relying on…

In safety-critical deep learning applications, robustness measures the ability of neural models that handle imperceptible perturbations in input data, which may lead to potential safety hazards. Existing pre-deployment robustness assessment…

Robust, faithful and harm-free pronoun use for individuals is an important goal for language model development as their use increases, but prior work tends to study only one or two of these characteristics at a time. To measure progress…

Recent natural language processing (NLP) techniques have accomplished high performance on benchmark datasets, primarily due to the significant improvement in the performance of deep learning. The advances in the research community have led…

In recent years, Large language model-powered Automated Program Repair (LAPR) techniques have achieved state-of-the-art bug-fixing performance and have been pervasively applied and studied in both industry and academia. Nonetheless, LLMs…

Retrieval-augmented generation (RAG) frameworks enable large language models (LLMs) to retrieve relevant information from a knowledge base and incorporate it into the context for generating responses. This mitigates hallucinations and…

Recently, Large Language Model (LLM)-empowered recommender systems have revolutionized personalized recommendation frameworks and attracted extensive attention. Despite the remarkable success, existing LLM-empowered RecSys have been…

Recently, NLP models have achieved remarkable progress across a variety of tasks; however, they have also been criticized for being not robust. Many robustness problems can be attributed to models exploiting spurious correlations, or…

Retrieval-Augmented Generation (RAG) grounds Large Language Models (LLMs) in external knowledge but often suffers from flat context representations and stateless retrieval, leading to unstable performance. We propose Stateful…

Software vulnerabilities are a primary threat to modern infrastructure. While static analysis and Graph Neural Networks have long served as the foundation for vulnerability detection, the emergence of Large Language Models (LLMs) has…

Large language models (LLMs) consistently achieve strong results on text-to-SQL benchmarks, but their robustness to schema variations remains poorly understood. Recent work suggests that the schema structure matters, but does not provide a…

The evaluation of Retrieval-Augmented Generation (RAG) systems typically examines retrieval quality and generation parameters like temperature in isolation, overlooking their interaction. This work presents a systematic investigation of how…

Speeded Up Robust Features (SURF) has emerged as one of the more popular feature descriptors and detectors in recent years. Performance and algorithmic details vary widely between implementations due to SURF's complexity and ambiguities…

Automated short-answer grading (ASAG) remains a challenging task due to the linguistic variability of student responses and the need for nuanced, rubric-aligned partial credit. While Large Language Models (LLMs) offer a promising solution,…

The predominant challenge in weakly supervised semantic parsing is that of spurious programs that evaluate to correct answers for the wrong reasons. Prior work uses elaborate search strategies to mitigate the prevalence of spurious…