paper-with-me

Papers

Artificial Impressions: Evaluating Large Language Model Behavior Through the Lens of Trait Impressions

2025-10-10 · Nicholas Deas, Kathleen McKeown arxiv

We introduce and study artificial impressions--patterns in LLMs' internal representations of prompts that resemble human impressions and stereotypes based on language. We fit linear probes on generated prompts to predict impressions according to the two-dimensional Stereotype Content Model (SCM). Using these probes, we study the relationship between impressions and downstream model behavior as well as prompt features that may inform such impressions. We find that LLMs inconsistently report impressions when prompted, but also that impressions are more consistently linearly decodable from their hidden representations. Additionally, we show that artificial impressions of prompts are predictive of the quality and use of hedging in model responses. We also investigate how particular content, stylistic, and dialectal features in prompts impact LLM impressions.

📄 PDF Abstract BibTeX arXiv:2510.08915

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Predicting Social Perception from Faces: A Deep Learning Approach

2019-06-29 · U. Messer, S. Fausser

Warmth and competence represent the fundamental traits in social judgment that determine emotional reactions and behavioral intentions towards social targets. This research investigates whether an algorithm can learn vis…

Deep LearningGeneral Classification

The current status of large language models in summarizing radiology report impressions

2024-06-04 · Danqing Hu, Shanyuan Zhang, Qing Liu, Xiaofeng Zhu 외

Large language models (LLMs) like ChatGPT show excellent capabilities in various natural language processing tasks, especially for text generation. The effectiveness of LLMs in summarizing radiology report impressions re…

Text Generation

Training Dialogue Systems by AI Feedback for Improving Overall Dialogue Impression

2025-01-22 · Kai Yoshida, Masahiro Mizukami, Seiya Kawano, Canasai Kruengkrai 외

To improve user engagement during conversations with dialogue systems, we must improve individual dialogue responses and dialogue impressions such as consistency, personality, and empathy throughout the entire dialogue. …

Evaluating Large Language Models for Radiology Natural Language Processing

2023-07-25 · Zhengliang Liu, Tianyang Zhong, Yiwei Li, Yutong Zhang 외

The rise of large language models (LLMs) has marked a pivotal shift in the field of natural language processing (NLP). LLMs have revolutionized a multitude of domains, and they have made a significant impact in the medic…

Automatic Personalized Impression Generation for PET Reports Using Large Language Models

2023-09-18 · Xin Tie, Muheon Shin, Ali Pirasteh, Nevein Ibrahim 외

In this study, we aimed to determine if fine-tuned large language models (LLMs) can generate accurate, personalized impressions for whole-body PET reports. Twelve language models were trained on a corpus of PET reports u…