Related papers: Do not be greedy, Think Twice: Sampling and Select…
Speculative decoding, which combines a draft model with a target model, has emerged as an effective approach to accelerate large language model (LLM) inference. However, existing methods often face a trade-off between the acceptance rate…
Question Aware Open Information Extraction (Question aware Open IE) takes question and passage as inputs, outputting an answer tuple which contains a subject, a predicate, and one or more arguments. Each field of answer is a natural…
Document-level relation extraction (DocRE) aims to extract semantic relations among entity pairs in a document. Typical DocRE methods blindly take the full document as input, while a subset of the sentences in the document, noted as the…
Event extraction is essential for event understanding and analysis. It supports tasks such as document summarization and decision-making in emergency scenarios. However, existing event extraction approaches have limitations: (1)…
Large Language Models (LLMs) excel at many tasks but often falter on complex problems that require structured, multi-step reasoning. We introduce the Diagram of Thought (DoT), a framework that enables a single LLM to build and navigate a…
Recent vision-language models (VLMs) achieve remarkable reasoning through reinforcement learning (RL), which provides a feasible solution for realizing continuous self-evolving large vision-language models (LVLMs) in the era of experience.…
Speculative decoding accelerates LLMs by using a lightweight draft model to generate tokens autoregressively before verifying them in parallel with a larger target model. However, determining the optimal number of tokens to draft remains a…
Our interest in this paper is in meeting a rapidly growing industrial demand for information extraction from images of documents such as invoices, bills, receipts etc. In practice users are able to provide a very small number of example…
Large language models (LLMs) suffer from high inference latency due to the auto-regressive decoding process. Speculative decoding accelerates inference by generating multiple draft tokens using a lightweight model and verifying them in…
Answering questions about images often requires combining visual understanding with external knowledge. Multimodal Large Language Models (MLLMs) provide a natural framework for this setting, but they often struggle to identify the most…
Unsupervised domain adaptation generalizes neural retrievers to an unseen domain by generating pseudo queries on target domain documents. The quality and efficiency of this adaptation critically depend on which documents are selected for…
This paper defines and explores the design space for information extraction (IE) from layout-rich documents using large language models (LLMs). The three core challenges of layout-aware IE with LLMs are 1) data structuring, 2) model…
Constructing accurate knowledge graphs from long texts and low-resource languages is challenging, as large language models (LLMs) experience degraded performance with longer input chunks. This problem is amplified in low-resource settings…
The prevailing approach to distilling reasoning from Large Language Models (LLMs)-behavioral cloning from textual rationales-is fundamentally limited. It teaches Small Language Models (SLMs) to mimic surface-level patterns rather than the…
Over recent years, an increasing amount of compute and data has been poured into training large language models (LLMs), usually by doing one-pass learning on as many tokens as possible randomly selected from large-scale web corpora. While…
Masked Diffusion Models (MDMs) enable flexible decoding orders, yet existing samplers remain largely greedy, selecting locally certain tokens without accounting for their downstream effects. We show that this myopia can increase cumulative…
A long standing goal of the data management community is to develop general, automated systems that ingest semi-structured documents and output queryable tables without human effort or domain specific customization. Given the sheer variety…
Frontier reasoning models have exhibited incredible capabilities across a wide array of disciplines, driven by posttraining large language models (LLMs) with reinforcement learning (RL). However, despite the widespread success of this…
Open Information Extraction (OpenIE) is the task of extracting (subject, predicate, object) triples from natural language sentences. Current OpenIE systems extract all triple slots independently. In contrast, we explore the hypothesis that…
A key bottleneck in building automatic extraction models for visually rich documents like invoices is the cost of acquiring the several thousand high-quality labeled documents that are needed to train a model with acceptable accuracy. We…