Related papers: RepoShapley: Shapley-Enhanced Context Filtering fo…
Long-tail learning has received significant attention in recent years due to the challenge it poses with extremely imbalanced datasets. In these datasets, only a few classes (known as the head classes) have an adequate number of training…
Retrieval-Augmented Generation (RAG) systems rely on retrieved documents being concatenated into a model's input context, making both document ordering and context size critical yet controversial design choices. Prior work reports…
The performance of repository-level code completion depends upon the effective leverage of both general and repository-specific knowledge. Despite the impressive capability of code LLMs in general code completion tasks, they often exhibit…
Current search techniques are limited to standard RAG query-document applications. In this paper, we propose a novel technique to expand the code and index for predicting the required APIs, directly enabling high-quality, end-to-end code…
Preference-based reward learning is widely used for shaping agent behavior to match a user's preference, yet its sparse binary feedback makes it especially vulnerable to causal confusion. The learned reward often latches onto spurious…
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge to generate a response within a context with improved accuracy and reduced hallucinations. However, multi-modal RAG systems face…
Chunking is a crucial preprocessing step in retrieval-augmented generation (RAG) systems, significantly impacting retrieval effectiveness across diverse datasets. In this study, we systematically evaluate fixed-size chunking strategies and…
Retrieval-Augmented Generation (RAG) enhances factual grounding in large language models (LLMs) by incorporating retrieved evidence, but LLM accuracy declines when long or noisy contexts exceed the model's effective attention span. Existing…
Retrieval-augmented generation (RAG) enhances large language models by incorporating context retrieved from external knowledge sources. While the effectiveness of the retrieval module is typically evaluated with relevance-based ranking…
Deep networks allow to obtain outstanding results in semantic segmentation, however they need to be trained in a single shot with a large amount of data. Continual learning settings where new classes are learned in incremental steps and…
Generative search engines based on large language models (LLMs) are replacing traditional search, fundamentally changing how information providers are compensated. To sustain this ecosystem, we need fair mechanisms to attribute and…
The effectiveness of Retrieval-Augmented Generation (RAG) is highly dependent on how documents are chunked, that is, segmented into smaller units for indexing and retrieval. Yet, commonly used "one-size-fits-all" approaches often fail to…
Cloze-style reading comprehension has been a popular task for measuring the progress of natural language understanding in recent years. In this paper, we design a novel multi-perspective framework, which can be seen as the joint training of…
Retrieval-augmented language models have demonstrated performance comparable to much larger models while requiring fewer computational resources. The effectiveness of these models crucially depends on the overlap between query and retrieved…
The growing complexity of Cyber-Physical Systems (CPS), together with increasingly available parallelism provided by multi-core chips, fosters the parallelization of simulation. Simulation speed-ups are expected from co-simulation and…
Retrieval-augmented generation (RAG) systems rely on retrieval models for identifying relevant contexts and answer generation models for utilizing those contexts. However, retrievers exhibit imperfect recall and precision, limiting…
Coalition formation concerns strategic collaborations of selfish agents that form coalitions based on their preferences. It is often assumed that coalitions are disjoint and preferences are fully known, which may not hold in practice. In…
Retrieval-Augmented Generation (RAG) aims to augment the capabilities of Large Language Models (LLMs) by retrieving and incorporate external documents or chunks prior to generation. However, even improved retriever relevance can brings…
Recent works in relation extraction (RE) have achieved promising benchmark accuracy; however, our adversarial attack experiments show that these works excessively rely on entities, making their generalization capability questionable. To…
Retrieval-augmented generation (RAG) improves large language model reliability by grounding generated responses in external evidence. However, RAG performance depends on the relevance of retrieved passages, the quality of evidence ranking,…