paper-with-me

Papers

On Semantic Cognition, Inductive Generalization, and Language Models

2021-11-04 · Kanishka Misra

My doctoral research focuses on understanding semantic knowledge in neural network models trained solely to predict natural language (referred to as language models, or LMs), by drawing on insights from the study of concepts and categories grounded in cognitive science. I propose a framework inspired by 'inductive reasoning,' a phenomenon that sheds light on how humans utilize background knowledge to make inductive leaps and generalize from new pieces of information about concepts and their properties. Drawing from experiments that study inductive reasoning, I propose to analyze semantic inductive generalization in LMs using phenomena observed in human-induction literature, investigate inductive behavior on tasks such as implicit reasoning and emergent feature recognition, and analyze and relate induction dynamics to the learned conceptual representation space.

📄 PDF Abstract BibTeX arXiv:2111.02603

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Survey of Inductive Reasoning for Large Language Models

2025-10-11 · Kedi Chen, Dezhao Ruan, Yuhao Dan, Yaoting Wang 외 arxiv

Reasoning is an important task for large language models (LLMs). Among all the reasoning paradigms, inductive reasoning is one of the fundamental types, which is characterized by its particular-to-general thinking proces…

Data Augmentation

Deeply Semantic Inductive Spatio-Temporal Learning

2016-08-09 · Jakob Suchan, Mehul Bhatt, Carl Schultz

We present an inductive spatio-temporal learning framework rooted in inductive logic programming. With an emphasis on visuo-spatial language, logic, and cognition, the framework supports learning with relational spatio-t…

Inductive logic programming

Language Models Need Inductive Biases to Count Inductively

2024-05-30 · Yingshan Chang, Yonatan Bisk

Counting is a fundamental example of generalization, whether viewed through the mathematical lens of Peano's axioms defining the natural numbers or the cognitive science literature for children learning to count. The arg…

State Space Models

Target Languages (vs. Inductive Biases) for Learning to Act and Plan

2021-09-15 · Hector Geffner

Recent breakthroughs in AI have shown the remarkable power of deep learning and deep reinforcement learning. These developments, however, have been tied to specific tasks, and progress in out-of-distribution generalizati…

Combinatorial OptimizationDeep Reinforcement LearningOut-of-Distribution Generalization

Inductive Generalization for Robotic Manipulation

2026-06-19 · Annabella Macaluso, Haochen Zhang, Ishaan Masilamony, Yingshan Chang 외 arxiv

Understanding the generalization capabilities of visuomotor policies is essential in the development of capable robotic agents. Generalizable models learn structures that transfer across domains. However, in practice, vi…