相关论文: IFIR: A Comprehensive Benchmark for Evaluating Ins…

Pretrained language models (PLMs) like BERT and GPT-4 have become the foundation for modern information retrieval (IR) systems. However, existing PLM-based IR models primarily rely on the knowledge learned during training for prediction,…

Instruction tuning has become a foundation for unlocking the capabilities of large-scale pretrained models and improving their performance on complex tasks. Thus, the construction of high-quality instruction datasets is crucial for…

Multimodal representation learning has garnered significant attention in the AI community, largely due to the success of large pre-trained multimodal foundation models like LLaMA, GPT, Mistral, and CLIP. These models have achieved…

This paper presents FoFo, a pioneering benchmark for evaluating large language models' (LLMs) ability to follow complex, domain-specific formats, a crucial yet underexamined capability for their application as AI agents. Despite LLMs'…

Retrieving semantically relevant documents in niche domains poses significant challenges for traditional TF-IDF-based systems, often resulting in low similarity scores and suboptimal retrieval performance. This paper addresses these…

Large language models (LLMs) could be valuable personal AI agents across various domains, provided they can precisely follow user instructions. However, recent studies have shown significant limitations in LLMs' instruction-following…

Neural ranking models for information retrieval (IR) use shallow or deep neural networks to rank search results in response to a query. Traditional learning to rank models employ machine learning techniques over hand-crafted IR features. By…

One of the main challenges in Interactive Information Retrieval (IIR) evaluation is the development and application of re-usable tools that allow researchers to analyze search behavior of real users in different environments and different…

Acquiring complex behaviors is essential for artificially intelligent agents, yet learning these behaviors in high-dimensional settings poses a significant challenge due to the vast search space. Traditional reinforcement learning (RL)…

Composed image retrieval (CIR) aims to retrieve a target image that depicts a reference image modified by a textual description. While recent vision-language models (VLMs) achieve promising CIR performance by embedding images and text into…

Recent studies proposed to leverage large language models (LLMs) with In-Context Learning (ICL) to handle code intelligence tasks without fine-tuning. ICL employs task instructions and a set of examples as demonstrations to guide the model…

Retrieval-Augmented Generation (RAG) has emerged as a key paradigm for enhancing large language models (LLMs) by incorporating external knowledge. However, current RAG methods face two limitations: (1) they only cover limited RAG scenarios.…

Neural networks with deep architectures have demonstrated significant performance improvements in computer vision, speech recognition, and natural language processing. The challenges in information retrieval (IR), however, are different…

End-to-end autonomous driving is typically built upon imitation learning (IL), yet its performance is constrained by the quality of human demonstrations. To overcome this limitation, recent methods incorporate reinforcement learning (RL)…

The ability to perform complex tasks from detailed instructions is a key to many remarkable achievements of our species. As humans, we are not only capable of performing a wide variety of tasks but also very complex ones that may entail…

Large language models (LLMs) often produce unsupported or unverifiable content, known as "hallucinations." To mitigate this, retrieval-augmented LLMs incorporate citations, grounding the content in verifiable sources. Despite such…

Recent work has shown logical background knowledge can be used in learning systems to compensate for a lack of labeled training data. Many methods work by creating a loss function that encodes this knowledge. However, often the logic is…

The ability of Large Language Models (LLMs) to precisely follow complex and fine-grained lexical instructions is a cornerstone of their utility and controllability. However, evaluating this capability remains a significant challenge.…

Composed Image Retrieval (CIR) aims to retrieve a target image based on a query composed of a reference image, and a relative caption that specifies the desired modification. Despite the rapid development of CIR models, their performance is…

While standard IR models are mainly designed to optimize relevance, real-world search often needs to balance additional objectives such as diversity and fairness. These objectives depend on inter-document interactions and are commonly…