paper-with-me

홈 › Papers

Leveraging a Cognitive Model to Measure Subjective Similarity of Human and GPT-4 Written Content

2024-08-30 · Tyler Malloy, Maria José Ferreira, Fei Fang, Cleotilde Gonzalez

Cosine similarity between two documents can be computed using token embeddings formed by Large Language Models (LLMs) such as GPT-4, and used to categorize those documents across a range of uses. However, these similarities are ultimately dependent on the corpora used to train these LLMs, and may not reflect subjective similarity of individuals or how their biases and constraints impact similarity metrics. This lack of cognitively-aware personalization of similarity metrics can be particularly problematic in educational and recommendation settings where there is a limited number of individual judgements of category or preference, and biases can be particularly relevant. To address this, we rely on an integration of an Instance-Based Learning (IBL) cognitive model with LLM embeddings to develop the Instance-Based Individualized Similarity (IBIS) metric. This similarity metric is beneficial in that it takes into account individual biases and constraints in a manner that is grounded in the cognitive mechanisms of decision making. To evaluate the IBIS metric, we also introduce a dataset of human categorizations of emails as being either dangerous (phishing) or safe (ham). This dataset is used to demonstrate the benefits of leveraging a cognitive model to measure the subjective similarity of human participants in an educational setting.

📄 PDF Abstract BibTeX arXiv:2409.00269

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Attention 설명 없음
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…
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 $x$…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

The semantic similarity ensemble

2014-01-11 · Andrea Ballatore, Michela Bertolotto, David C. Wilson

Computational measures of semantic similarity between geographic terms provide valuable support across geographic information retrieval, data mining, and information integration. To date, a wide variety of approaches to …

Information RetrievalRetrievalSemantic SimilaritySemantic Textual Similarity

The Other Mind: How Language Models Exhibit Human Temporal Cognition

2025-07-21 · Lingyu Li, Yang Yao, Yixu Wang, Chubo Li 외 arxiv

As Large Language Models (LLMs) continue to advance, they exhibit certain cognitive patterns similar to those of humans that are not directly specified in training data. This study investigates this phenomenon by focusin…

MulCogBench: A Multi-modal Cognitive Benchmark Dataset for Evaluating Chinese and English Computational Language Models

2024-03-02 · Yunhao Zhang, Xiaohan Zhang, Chong Li, Shaonan Wang 외

Pre-trained computational language models have recently made remarkable progress in harnessing the language abilities which were considered unique to humans. Their success has raised interest in whether these models repr…

Mimicking Human Intuition: Cognitive Belief-Driven Q-Learning

2024-10-02 · Xingrui Gu, Guanren Qiao, Chuyi Jiang, Tianqing Xia 외

Reinforcement learning encounters challenges in various environments related to robustness and explainability. Traditional Q-learning algorithms cannot effectively make decisions and utilize the historical learning exper…

Decision MakingQ-Learning

Anthropomorphism and Trust in Human-Large Language Model interactions

2026-03-01 · Akila Kadambi, Ylenia D'Elia, Tanishka Shah, Iulia Comsa 외 arxiv

With large language models (LLMs) becoming increasingly prevalent in daily life, so too has the tendency to attribute to them human-like minds and emotions, or anthropomorphize them. Here, we investigate dimensions peopl…