Related papers: FollowTable: A Benchmark for Instruction-Following…

The increasing volume of academic literature makes it essential for researchers to organize, compare, and contrast collections of documents. Large language models (LLMs) can support this process by generating schemas defining shared aspects…

One of the core problems in large-scale recommendations is to retrieve top relevant candidates accurately and efficiently, preferably in sub-linear time. Previous approaches are mostly based on a two-step procedure: first learn an…

Reachability queries ask whether there exists a path from the source vertex to the target vertex on a graph. Recently, several powerful reachability queries, such as Label-Constrained Reachability (LCR) queries and Regular Path Queries…

Instruction tuning is essential for aligning large language models (LLMs) to downstream tasks and commonly relies on large, diverse corpora. However, small, high-quality subsets, known as coresets, can deliver comparable or superior…

Information retrieval systems have traditionally optimized for topical relevance-the degree to which retrieved documents match a query. However, relevance only approximates a deeper goal: utility, namely, whether retrieved information helps…

Instruction following is one of the fundamental capabilities of large language models (LLMs). As the ability of LLMs is constantly improving, they have been increasingly applied to deal with complex human instructions in real-world…

Most neural Information Retrieval (Neu-IR) models derive query-to-document ranking scores based on term-level matching. Inspired by TileBars, a classical term distribution visualization method, in this paper, we propose a novel Neu-IR model…

Rubric-based Reinforcement Learning (RL) has emerged as a promising approach for aligning Large Language Models (LLMs) with complex, open-domain instruction following tasks. However, existing methods predominantly rely on response-level…

Large Language Models (LLMs) have advanced Table Question Answering, where most queries can be answered by extracting information or simple aggregation. However, a common class of real-world queries is implicitly predictive, requiring the…

In the field of Image-Text Retrieval (ITR), recent advancements have leveraged large-scale Vision-Language Pretraining (VLP) for Fine-Grained (FG) instance-level retrieval, achieving high accuracy at the cost of increased computational…

Audio-text retrieval (ATR), which retrieves a relevant caption given an audio clip (A2T) and vice versa (T2A), has recently attracted much research attention. Existing methods typically aggregate information from each modality into a single…

Evaluating the ability of large language models (LLMs) to follow complex human-written instructions is essential for their deployment in real-world applications. While benchmarks like Chatbot Arena use human judges to assess model…

Retrieval augmentation is critical when Language Models (LMs) exploit non-parametric knowledge related to the query through external knowledge bases before reasoning. The retrieved information is incorporated into LMs as context alongside…

Large Language Models (LLMs) excel in general tasks, but adapting them to specialized domains relies on high-quality supervised fine-tuning (SFT) data. Although existing methods can identify subsets of high-quality data and reduce training…

Tables are recognized for their high information density and widespread usage, serving as essential sources of information. Seeking information from tables (TIS) is a crucial capability for Large Language Models (LLMs), serving as the…

Semantic textual similartiy (STS) and information retrieval tasks (IR) tasks have been the two major avenues to record the progress of embedding models in the past few years. Under the emerging Retrieval-augmented Generation (RAG) paradigm,…

Information retrieval aims to find information that meets users' needs from the corpus. Different needs correspond to different IR tasks such as document retrieval, open-domain question answering, retrieval-based dialogue, etc., while they…

The increasing acceptance of large language models (LLMs) as an alternative to knowledge sources marks a significant paradigm shift across various domains, including time-sensitive fields such as law, healthcare, and finance. To fulfill…

Tabular data is arguably one of the most commonly used data structures in various practical domains, including finance, healthcare and e-commerce. The inherent heterogeneity allows tabular data to store rich information. However, based on a…

With the growing popularity of LLM agents and RAG, it has become increasingly important to retrieve documents that are essential for solving a task, even when their connection to the task is indirect or implicit. Addressing this problem…