paper-with-me

홈 › Papers

Personality Profiling of Fictional Characters using Sense-Level Links between Lexical Resources

2015-09-01 · EMNLP 2015 9 · Lucie Flekova, Iryna Gurevych
📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Recommendation SystemsText Classification

Similar Papers 제목 키워드 기반

Personality Traits Recognition in Literary Texts

2019-08-01 · WS 2019 8 · Daniele Pizzolli, Carlo Strapparava

Interesting stories often are built around interesting characters. Finding and detailing what makes an interesting character is a real challenge, but certainly a significant cue is the character personality traits. Our e…

BIG-bench Machine Learning

MBTI Personality Prediction for Fictional Characters Using Movie Scripts

2022-10-20 · Yisi Sang, Xiangyang Mou, Mo Yu, Dakuo Wang 외

An NLP model that understands stories should be able to understand the characters in them. To support the development of neural models for this purpose, we construct a benchmark, Story2Personality. The task is to predict…

Predictiontext-classificationText Classification

Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works

2024-04-19 · Xinfeng Yuan, Siyu Yuan, Yuhan Cui, Tianhe Lin 외

Large language models (LLMs) have demonstrated impressive performance and spurred numerous AI applications, in which role-playing agents (RPAs) are particularly popular, especially for fictional characters. The prerequis…

ALOHA: Artificial Learning of Human Attributes for Dialogue Agents

2019-10-18 · Aaron W. Li, Veronica Jiang, Steven Y. Feng, Julia Sprague 외

For conversational AI and virtual assistants to communicate with humans in a realistic way, they must exhibit human characteristics such as expression of emotion and personality. Current attempts toward constructing huma…

Community DetectionLanguage ModellingRetrieval

Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects

2026-03-04 · Ji-Lun Peng, Yun-Nung Chen arxiv

Large Language Models (LLMs) have shown remarkable potential in developing role-playing agents (RPAs). However, current evaluation frameworks rely heavily on well-known fictional characters, raising a critical concern: m…