Relational Reasoning

149 papers with code • 1 benchmarks • 12 datasets

The goal of Relational Reasoning is to figure out the relationships among different entities, such as image pixels, words or sentences, human skeletons or interactive moving agents.

Source: Social-WaGDAT: Interaction-aware Trajectory Prediction via Wasserstein Graph Double-Attention Network

Libraries

Use these libraries to find Relational Reasoning models and implementations

Latest papers with no code

Interactive Autonomous Navigation with Internal State Inference and Interactivity Estimation

no code yet • 27 Nov 2023

Moreover, we propose an interactivity estimation mechanism based on the difference between predicted trajectories in these two situations, which indicates the degree of influence of the ego agent on other agents.

Large Language Models can Learn Rules

no code yet • 10 Oct 2023

In the deduction stage, the LLM is then prompted to employ the learned rule library to perform reasoning to answer test questions.

A Novel Neural-symbolic System under Statistical Relational Learning

no code yet • 16 Sep 2023

A key objective in field of artificial intelligence is to develop cognitive models that can exhibit human-like intellectual capabilities.

Quantifying and Attributing the Hallucination of Large Language Models via Association Analysis

no code yet • 11 Sep 2023

Although demonstrating superb performance on various NLP tasks, large language models (LLMs) still suffer from the hallucination problem, which threatens the reliability of LLMs.

Lifted Inference beyond First-Order Logic

no code yet • 22 Aug 2023

We expand a vast array of previous results in discrete mathematics literature on directed acyclic graphs, phylogenetic networks, etc.

CommonsenseVIS: Visualizing and Understanding Commonsense Reasoning Capabilities of Natural Language Models

no code yet • 23 Jul 2023

Specifically, we extract relevant commonsense knowledge in inputs as references to align model behavior with human knowledge.

LightPath: Lightweight and Scalable Path Representation Learning

no code yet • 19 Jul 2023

Next, we propose a relational reasoning framework to enable faster training of more robust sparse path encoders.

Statistical relational learning and neuro-symbolic AI: what does first-order logic offer?

no code yet • 8 Jun 2023

In this paper, our aim is to briefly survey and articulate the logical and philosophical foundations of using (first-order) logic to represent (probabilistic) knowledge in a non-technical fashion.

Continual Reasoning: Non-Monotonic Reasoning in Neurosymbolic AI using Continual Learning

no code yet • 3 May 2023

In this paper, we show that by combining a neural-symbolic system with methods from continual learning, LTN can obtain a higher level of accuracy when addressing non-monotonic reasoning tasks.