Related papers: Extract-0: A Specialized Language Model for Docume…

We cast a suite of information extraction tasks into a text-to-triple translation framework. Instead of solving each task relying on task-specific datasets and models, we formalize the task as a translation between task-specific input text…

Reinforcement learning is a promising approach for learning control policies for robot tasks. However, specifying complex tasks (e.g., with multiple objectives and safety constraints) can be challenging, since the user must design a reward…

Neural models trained with large amount of parallel data have achieved impressive performance in abstractive summarization tasks. However, large-scale parallel corpora are expensive and challenging to construct. In this work, we introduce a…

Domain experts often need to extract structured information from large corpora. We advocate for a search paradigm called ``extractive search'', in which a search query is enriched with capture-slots, to allow for such rapid extraction. Such…

Information extraction from conversational data is particularly challenging because the task-centric nature of conversation allows for effective communication of implicit information by humans, but is challenging for machines. The…

Information extraction and textual comprehension from materials literature are vital for developing an exhaustive knowledge base that enables accelerated materials discovery. Language models have demonstrated their capability to answer…

Extractive models usually formulate text summarization as extracting fixed top-$k$ salient sentences from the document as a summary. Few works exploited extracting finer-grained Elementary Discourse Unit (EDU) with little analysis and…

We propose ERFSL, an efficient reward function searcher using large language models (LLMs) for custom-environment, multi-objective learning-based methods (LB). ERFSL generates reward components based on explicit user requirements, rectifies…

General-purpose open-domain dense retrieval systems are usually trained with a large, eclectic mix of corpora and search tasks. How should these diverse corpora and tasks be sampled for training? Conventional approaches sample them…

Effective information retrieval requires reasoning over partial evidence and refining strategies as information emerges. Yet current approaches fall short: neural retrievers lack reasoning capabilities, large language models (LLMs) provide…

Event Argument Extraction (EAE) is an extremely difficult information extraction problem -- with significant limitations in few-shot cross-domain (FSCD) settings. A common solution to FSCD modeling is data augmentation. Unfortunately,…

The inherent ambiguity of cause and effect boundaries poses a challenge in evaluating causal event extraction tasks. Traditional metrics like Exact Match and BertScore poorly reflect model performance, so we trained evaluation models to…

Reasoning abilities, especially those for solving complex math problems, are crucial components of general intelligence. Recent advances by proprietary companies, such as o-series models of OpenAI, have made remarkable progress on reasoning…

Reranking is fundamental to information retrieval and retrieval-augmented generation, with recent Large Language Models (LLMs) significantly advancing reranking quality. Most current works rely on large-scale LLMs (>7B parameters),…

Domain dependence and annotation subjectivity pose challenges for supervised keyword extraction. Based on the premises that second-order keyness patterns are existent at the community level and learnable from annotated keyword extraction…

Large language models (LLMs) and their associated agent-based frameworks have significantly advanced automated information extraction, a critical component of modern recommender systems. While these multitask frameworks are widely used in…

Optimizing communication topology is fundamental to the efficiency and effectiveness of Large Language Model (LLM)-based Multi-Agent Systems (MAS). While recent approaches utilize reinforcement learning to dynamically construct…

Document-level relation extraction (DocRE) attracts more research interest recently. While models achieve consistent performance gains in DocRE, their underlying decision rules are still understudied: Do they make the right predictions…

Extractive summarization produces summaries by identifying and concatenating the most important sentences in a document. Since most summarization datasets do not come with gold labels indicating whether document sentences are…

Retrieval-Augmented Generation (RAG) systems face significant performance gaps when applied to technical domains requiring precise information extraction from complex documents. Current evaluation methodologies relying on document-level…