Related papers: Halo: Domain-Aware Query Optimization for Long-Con…

Existing open-domain question answering (QA) models are not suitable for real-time usage because they need to process several long documents on-demand for every input query. In this paper, we introduce the query-agnostic indexable…

As web agents (e.g., Deep Research) routinely consume massive volumes of web pages to gather and analyze information, LLM context management -- under large token budgets and low signal density -- emerges as a foundational, high-importance,…

Retrieval-augmented generation (RAG) has become integral to large language models (LLMs), particularly for conversational AI systems where user questions may reference knowledge beyond the LLMs' training cutoff. However, many natural user…

In today's digital world, seeking answers to health questions on the Internet is a common practice. However, existing question answering (QA) systems often rely on using pre-selected and annotated evidence documents, thus making them…

Long document summarization poses a significant challenge in natural language processing due to input lengths that exceed the capacity of most state-of-the-art pre-trained language models. This study proposes a hierarchical framework that…

Document-based question answering (QA) increasingly includes abstract questions that require synthesizing scattered information from long documents or across multiple documents into coherent answers. However, this setting is still poorly…

Retrieval-Augmented Large Language Models (LLMs), which incorporate the non-parametric knowledge from external knowledge bases into LLMs, have emerged as a promising approach to enhancing response accuracy in several tasks, such as…

On-the-fly retrieval of relevant knowledge has proven an essential element of reliable systems for tasks such as open-domain question answering and fact verification. However, because retrieval systems are not perfect, generation models are…

Long-horizon tasks that require sustained reasoning and multiple tool interactions remain challenging for LLM agents: small errors compound across steps, and even state-of-the-art models often hallucinate or lose coherence. We identify…

Conventional RAG is considered one of the most effective methods for addressing model knowledge insufficiency and hallucination, particularly in the judicial domain that requires high levels of knowledge rigor, logical consistency, and…

Effective e-commerce risk management requires in-depth case investigations to identify emerging fraud patterns in highly adversarial environments. However, manual investigation typically requires analyzing the associations and couplings…

Retrieval-augmented generation (RAG) with large language models (LLMs) is especially valuable in specialized domains, where precision is critical. To more specialize the LLMs into a target domain, domain-specific RAG has recently been…

This paper presents the Long Context and Form Output (LCFO) benchmark, a novel evaluation framework for assessing gradual summarization and summary expansion capabilities across diverse domains. LCFO consists of long input documents (5k…

Large Language Models (LLMs) perform well on standard reasoning and question-answering benchmarks, yet such evaluations often fail to capture their ability to handle long-tail, expertise-intensive knowledge in real-world professional…

Identifying relevant knowledge to be used in conversational systems that are grounded in long documents is critical to effective response generation. We introduce a knowledge identification model that leverages the document structure to…

A Retrieval-Augmented Generation (RAG)-based question-answering (QA) system enhances a large language model's knowledge by retrieving relevant documents based on user queries. Discrepancies between user queries and document phrasings often…

Dialogue systems can leverage large pre-trained language models and knowledge to generate fluent and informative responses. However, these models are still prone to produce hallucinated responses not supported by the input source, which…

Though current long-context large language models (LLMs) have demonstrated impressive capacities in answering user questions based on extensive text, the lack of citations in their responses makes user verification difficult, leading to…

Large language models (LLMs) have revolutionized natural language processing by solving a wide range of tasks simply guided by a prompt. Yet their performance is highly sensitive to prompt formulation. While automatic prompt optimization…

Retrieval-Augmented Generation (RAG) offers a promising solution to address various limitations of Large Language Models (LLMs), such as hallucination and difficulties in keeping up with real-time updates. This approach is particularly…