paper-with-me

홈 › Papers

Text Understanding in GPT-4 vs Humans

2024-03-25 · Thomas R. Shultz, Jamie M. Wise, Ardavan Salehi Nobandegani

We examine whether a leading AI system GPT4 understands text as well as humans do, first using a well-established standardized test of discourse comprehension. On this test, GPT4 performs slightly, but not statistically significantly, better than humans given the very high level of human performance. Both GPT4 and humans make correct inferences about information that is not explicitly stated in the text, a critical test of understanding. Next, we use more difficult passages to determine whether that could allow larger differences between GPT4 and humans. GPT4 does considerably better on this more difficult text than do the high school and university students for whom these the text passages are designed, as admission tests of student reading comprehension. Deeper exploration of GPT4 performance on material from one of these admission tests reveals generally accepted signatures of genuine understanding, namely generalization and inference.

📄 PDF Abstract BibTeX arXiv:2403.17196

Code (0)

등록된 구현이 없습니다.

Tasks

Reading Comprehension

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Humans Perceive Wrong Narratives from AI Reasoning Texts

2025-08-09 · Mosh Levy, Zohar Elyoseph, Yoav Goldberg arxiv

A new generation of AI models generates step-by-step reasoning text before producing an answer. This text appears to offer a human-readable window into their computation process, and is increasingly relied upon for trans…

ProSPer: Probing Human and Neural Network Language Model Understanding of Spatial Perspective

2021-11-01 · EMNLP (BlackboxNLP) 2021 11 · Tessa Masis, Carolyn Anderson

Understanding perspectival language is important for applications like dialogue systems and human-robot interaction. We propose a probe task that explores how well language models understand spatial perspective. We prese…

Language ModelingLanguage Modelling

Cognitive Perspectives on Context-based Decisions and Explanations

2021-01-25 · Marcus Westberg, Kary Främling

When human cognition is modeled in Philosophy and Cognitive Science, there is a pervasive idea that humans employ mental representations in order to navigate the world and make predictions about outcomes of future action…

Decision MakingExplainable Artificial Intelligence (XAI)NavigatePhilosophy

HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs

2025-08-14 · Zheng Qin, Ruobing Zheng, Yabing Wang, Tianqi Li 외 arxiv

While Multimodal Large Language Models (MLLMs) show immense promise for achieving truly human-like interactions, progress is hindered by the lack of fine-grained evaluation frameworks for human-centered scenarios, encomp…

Reinforcement Learning

Dissonance Between Human and Machine Understanding

2021-01-18 · Zijian Zhang, Jaspreet Singh, Ujwal Gadiraju, Avishek Anand

Complex machine learning models are deployed in several critical domains including healthcare and autonomous vehicles nowadays, albeit as functional black boxes. Consequently, there has been a recent surge in interpretin…

AttributeAutonomous Vehiclesfeature selectionimage-classification+1