ZoekresultatenZoekresultaten
Volg ons op
Volg ons op
Types
0Instelling
26Publicatiejaar
6Producttype
19Bestandstype
9Taal
5Onderzoeksthema's
13Publicaties met bestand/URL
2Projectstatus
3Detective stories are a particularly popular form of mystery fiction driven by investigative reasoning and the gradual revelation of hidden truths. This work presents a trait-guided method for generating detective stories that reflect the investigative styles of classic fictional detectives while maintaining narrative quality. Building upon a preliminary study that characterized the investigative methods of seven iconic detectives (Hercule Poirot, Sherlock Holmes, William Murdoch, Columbo, Father Brown, Miss Marple, and Auguste Dupin), we developed a new narrative generation approach that uses formalized investigative trait profiles and Large Language Models (LLMs) to write detective stories. The method integrates these profiles with narrative principles grounded in literary theory, particularly Todorov’s dual narrative structure, to produce stories where selected detectives solve crimes according to their characteristic investigative approaches. We conducted a two-phase evaluation study with 210 trait-guided stories to assess both the recognizability of detective-specific investigative styles and the overall narrative quality of the generated stories. In Phase 1, state-of-the-art language models achieved 82.4% accuracy in identifying detectives from anonymized narratives based on investigative characteristics, with 78.8% accuracy when restricted to investigative methods alone, demonstrating that the generated stories successfully embedded recognizable investigative styles. In Phase 2, LLM-based quality evaluation revealed that trait-guided stories achieved higher scores than stories generated without trait guidance on empathy, coherence, surprise, and complexity, with length-controlled analyses confirming robust condition effects on empathy and coherence, and particularly strong improvements for psychologically-oriented detectives. A preliminary human validation supported the central empathy finding and indicated that the trait-guided method’s benefits on surprise and engagement may be more pronounced than the LLM scores alone suggest. These findings demonstrate that computational methods can generate detective narratives that preserve distinctive investigative styles while enhancing character depth and emotional portrayal, contributing to the field of computational narratology and AI-assisted creative writing.
ARTIKEL
Faults silently degrade HVAC performance, wasting energy and diminishing indoor well-being. How can artificial intelligence help us diagnose them? This paper shares insights into challenges of large-scale practical HVAC diagnostics and presents efforts from the Brains4Buildings project, specifically highlighting the emerging potential of Large Language Models (LLMs) as intelligent assistants toward self-learning and adaptive diagnostics.
ARTIKEL
Agent-based modeling (ABM) is a powerful tool for simulating building users’ dynamic behavior in demand response (DR) programs. However, ABM faces several challenges, particularly in encoding building users’ natural language features and common sense into rules or mathematical equations. To overcome these limitations, this paper proposes an agent framework based on large language models (LLMs) to simulate building users’ air-conditioning setpoint adjustment behavior under DR. This framework leverages LLMs’ natural language processing capabilities to replicate building users’ reasoning and decision making processes. It consists of five modules: persona, perception, decision, reflection, and memory. Agents are assigned diverse personas through natural language descriptions based on empirical survey data. LLMs drive agents to reason and make decisions based on incentive prices and historical experiences. The results show that the LLM-based agent has common sense derived from natural language-defined personas and exhibits human-like irrational characteristics. This demonstrates the feasibility of replacing rules with natural language in ABM. The LLM-based agent can more effectively model hard-to-parameterize human features and provide decision explanations through LLM outputs. The results show that the inclusion of reflection and memory modules enables the agent to learn from previous decisions and reduce unreasonable choices.
ARTIKEL
Agent-based modeling (ABM) is a powerful tool for simulating building users’ dynamic behavior in demand response (DR) programs. However, ABM faces several challenges, particularly in encoding building users’ natural language features and common sense into rules or mathematical equations. To overcome these limitations, this paper proposes an agent framework based on large language models (LLMs) to simulate building users’ air-conditioning setpoint adjustment behavior under DR. This framework leverages LLMs’ natural language processing capabilities to replicate building users’ reasoning and decision making processes. It consists of five modules: persona, perception, decision, reflection, and memory. Agents are assigned diverse personas through natural language descriptions based on empirical survey data. LLMs drive agents to reason and make decisions based on incentive prices and historical experiences. The results show that the LLM-based agent has common sense derived from natural language-defined personas and exhibits human-like irrational characteristics. This demonstrates the feasibility of replacing rules with natural language in ABM. The LLM-based agent can more effectively model hard-to-parameterize human features and provide decision explanations through LLM outputs. The results show that the inclusion of reflection and memory modules enables the agent to learn from previous decisions and reduce unreasonable choices.
ARTIKEL
This study explores the integration of Large Language Models (LLMs) and speech-processing technologies in humanoid robots to support during university open days. We implemented an AI-driven assistant on the Pepper and NAO robot to provide information to open day visitors. The system employs real-time speech recognition using OpenAI’s Whisper, dialogue validation with GPT-4, and a Retrieval-Augmented Generation (RAG) approach to ensure accurate and context-aware responses. An exploratory observational study revealed positive user engagement, with many participants expressing surprise at the conversational abilities of the robot. However, challenges such as background noise, response latency, and user distrust were also observed. These findings suggest that LLM-powered robotic assistants can enhance visitor experiences in educational settings, suggesting areas for improvement in responsiveness, non-verbal interaction, and trust-building.
CONFERENTIEBIJDRAGE
This paper presents a generative large language model (LLM)- guided approach to detect discursive patterns in Dutch social media.
CONFERENTIEBIJDRAGE
Post-training quantization reduces the computational demand of Large Language Models (LLMs) but can weaken some of their capabilities. Since LLM abilities emerge with scale, smaller LLMs are more sensitive to quantization. In this paper, we explore how quantization affects smaller LLMs’ ability to perform retrieval-augmented generation (RAG), specifically in longer contexts. We chose personalization for evaluation because it is a challenging domain to perform using RAG as it requires long-context reasoning over multiple documents. We compare the original FP16 and the quantized INT4 performance of multiple 7B and 8B LLMs on two tasks while progressively increasing the number of retrieved documents to test how quantized models fare against longer contexts. To better understand the effect of retrieval, we evaluate three retrieval models in our experiments. Our findings reveal that if a 7B LLM performs the task well, quantization does not impair its performance and long-context reasoning capabilities. We conclude that it is possible to utilize RAG with quantized smaller LLMs.
CONFERENTIEBIJDRAGE
Psychologists, psycholinguists, and other researchers using language stimuli have been struggling for more than 30 years with the problem of how to analyze experimental data that contain two crossed random effects (items and participants). The classical analysis of variance does not apply; alternatives have been proposed but have failed to catch on, and a statistically unsatisfactory procedure of using two approximations (known as F 1 and F 2) has become the standard. A simple and elegant solution using mixed model analysis has been available for 15 years, and recent improvements in statistical software have made mixed models analysis widely available. The aim of this article is to increase the use of mixed models by giving a concise practical introduction and by giving clear directions for undertaking the analysis in the most popular statistical packages. The article also introduces the djmixed add-on package for SPSS, which makes entering the models and reporting their results as straightforward as possible.
ARTIKEL
This article investigates gender bias in narratives generated by Large Language Models (LLMs) through a two-phase study. Building on our existing work in narrative generation, we employ a structured methodology to analyze the influence of protagonist gender on both the generation and classification of fictional stories. In Phase 1, factual narratives were generated using six LLMs, guided by predefined narrative structures (Hero's Journey and Heroine's Journey). Gender bias was quantified through specialized metrics and statistical analyses, revealing significant disparities in protagonist gender distribution and associations with narrative archetypes. In Phase 2, counterfactual narratives were constructed by altering the protagonists’ genders while preserving all other narrative elements. These narratives were then classified by the same LLMs to assess how gender influences their interpretation of narrative structures. Results indicate that LLMs exhibit difficulty in disentangling the protagonist's gender from the narrative structure, often using gender as a heuristic to classify stories. Male protagonists in emotionally driven narratives were frequently misclassified as following the Heroine's Journey, while female protagonists in logic-driven conflicts were misclassified as adhering to the Hero's Journey. These findings provide empirical evidence of embedded gender biases in LLM-generated narratives, highlighting the need for bias mitigation strategies in AI-driven storytelling to promote diversity and inclusivity in computational narrative generation.
ARTIKEL
