paper-with-me

Papers

Multi-step Inference over Unstructured Data

2024-06-26 · Aditya Kalyanpur, Kailash Karthik Saravanakumar, Victor Barres, CJ McFate, Lori Moon, Nati Seifu, Maksim Eremeev, Jose Barrera, Abraham Bautista-Castillo, Eric Brown, David Ferrucci

The advent of Large Language Models (LLMs) and Generative AI has revolutionized natural language applications across various domains. However, high-stakes decision-making tasks in fields such as medical, legal and finance require a level of precision, comprehensiveness, and logical consistency that pure LLM or Retrieval-Augmented-Generation (RAG) approaches often fail to deliver. At Elemental Cognition (EC), we have developed a neuro-symbolic AI platform to tackle these problems. The platform integrates fine-tuned LLMs for knowledge extraction and alignment with a robust symbolic reasoning engine for logical inference, planning and interactive constraint solving. We describe Cora, a Collaborative Research Assistant built on this platform, that is designed to perform complex research and discovery tasks in high-stakes domains. This paper discusses the multi-step inference challenges inherent in such domains, critiques the limitations of existing LLM-based methods, and demonstrates how Cora's neuro-symbolic approach effectively addresses these issues. We provide an overview of the system architecture, key algorithms for knowledge extraction and formal reasoning, and present preliminary evaluation results that highlight Cora's superior performance compared to well-known LLM and RAG baselines.

📄 PDF Abstract BibTeX arXiv:2406.17987

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingRAGRetrievalRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Weight Decay 설명 없음
WordPiece 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Question Answering via Integer Programming over Semi-Structured Knowledge

2016-04-20 · Daniel Khashabi, Tushar Khot, Ashish Sabharwal, Peter Clark 외

Answering science questions posed in natural language is an important AI challenge. Answering such questions often requires non-trivial inference and knowledge that goes beyond factoid retrieval. Yet, most systems for th…

Information RetrievalQuestion AnsweringRetrieval

KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using Large Language Models

2023-10-17 · Jiho Kim, Yeonsu Kwon, Yohan Jo, Edward Choi

While large language models (LLMs) have made considerable advancements in understanding and generating unstructured text, their application in structured data remains underexplored. Particularly, using LLMs for complex r…

Fact VerificationKnowledge GraphsRetrievalSentence+1

ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling

2025-10-16 · Jianghao Lin, Yuanyuan Shi, Xin Peng, Renjie Ding 외 arxiv

Large language models (LLMs) excel at function calling, but inference scaling has been explored mainly for unstructured generation. We propose an inference-scaling framework for structured outputs that combines fine-grai…

Deep Multi-Modal Structural Equations For Causal Effect Estimation With Unstructured Proxies

2022-03-18 · Shachi Deshpande, Kaiwen Wang, Dhruv Sreenivas, Zheng Li 외

Estimating the effect of intervention from observational data while accounting for confounding variables is a key task in causal inference. Oftentimes, the confounders are unobserved, but we have access to large amounts …

Causal InferenceTime Series Analysis

Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanics

2025-06-06 · Tobias Würth, Niklas Freymuth, Gerhard Neumann, Luise Kärger

Graph-based learned simulators have emerged as a promising approach for simulating physical systems on unstructured meshes, offering speed and generalization across diverse geometries. However, they often struggle with c…

DenoisingGraph Neural Network