Tootfinder

The Compositional Architecture of Regret in Large Language Models
Xiangxiang Cui, Shu Yang, Tianjin Huang, Wanyu Lin, Lijie Hu, Di Wang
https://arxiv.org/abs/2506.15617

The Compositional Architecture of Regret in Large Language Models
Regret in Large Language Models refers to their explicit regret expression when presented with evidence contradicting their previously generated misinformation. Studying the regret mechanism is crucial for enhancing model reliability and helps in revealing how cognition is coded in neural networks. To understand this mechanism, we need to first identify regret expressions in model outputs, then analyze their internal representation. This analysis requires examining the model's hidden states, wh…

PBPU Elastomer Network Architecture Determination via Corresponding States Analysis of Mechanical Behavior
Sushanta Das (Department of Chemical Engineering, Indian Institute of Technology Bombay, Mumbai, Maharashtra, India Defence Research,Development Organization, New Delhi, India), Hari Ramakrishna Sudhakar (Department of Chemical Engineering, Indian Institute of Technology Bombay, Mumbai, Maharashtra, India), Hemant Nanavati (Department of Chemical Engineering, Indian Institute of T…

PBPU Elastomer Network Architecture Determination via Corresponding States Analysis of Mechanical Behavior
In this work we examine the effect of R=[NCO]/[OH] in the R=<1 regime, on the resultant structural topology of polybutadiene polyurethane (PBPU) elastomer networks based on hydroxy-terminated polybutadiene (HTPB). We employ stress-elongation behavior and its modeling, as a tool. We examine this property via a combination of our model for the finite chain phantom networks incorporating the HTPB structural information, with the slip-tube model from the literature, suitably modified phenomenologic…

Combining stated and revealed preferences
Romuald Meango, Marc Henry, Ismael Mourifie
https://arxiv.org/abs/2507.13552 https://arxiv.…

Combining stated and revealed preferences
Can stated preferences inform counterfactual analyses of actual choice? This research proposes a novel approach to researchers who have access to both stated choices in hypothetical scenarios and actual choices, matched or unmatched. The key idea is to use stated choices to identify the distribution of individual unobserved heterogeneity. If this unobserved heterogeneity is the source of endogeneity, the researcher can correct for its influence in a demand function estimation using actual choic…

Temporal Network Analysis of Microservice Architectural Degradation
Alexander Bakhtin
https://arxiv.org/abs/2508.11571 https://arxiv.org/pdf/2508.11571

Temporal Network Analysis of Microservice Architectural Degradation
Microservice architecture can be modeled as a network of microservices making calls to each other, commonly known as the service dependency graph. Network Science can provide methods to study such networks. In particular, temporal network analysis is a branch of Network Science that analyzes networks evolving with time. In microservice systems, temporal networks can arise if we examine the architecture of the system across releases or monitor a deployed system using tracing. In this research …

Human-AI collaboration or obedient and often clueless AI in instruct, serve, repeat dynamics?
Mohammed Saqr, Kamila Misiejuk, Sonsoles L\'opez-Pernas
https://arxiv.org/abs/2508.10919

Human-AI collaboration or obedient and often clueless AI in instruct, serve, repeat dynamics?
While research on human-AI collaboration exists, it mainly examined language learning and used traditional counting methods with little attention to evolution and dynamics of collaboration on cognitively demanding tasks. This study examines human-AI interactions while solving a complex problem. Student-AI interactions were qualitatively coded and analyzed with transition network analysis, sequence analysis and partial correlation networks as well as comparison of frequencies using chi-square an…

Quantifying Diagnostic Signal Decay in Dementia: A National Study of Medicare Hospitalization Data
Federica Spoto, Jiazi Tian, Jonas H\"ugel, Daniel T. Ortega, Christine S. Ritchie, Deborah Blacker, Francesca Dominici, Chirag J. Patel, Daniel Mork, Hossein Estiri
https://arxiv.org/abs/2506.14669

Quantifying Diagnostic Signal Decay in Dementia: A National Study of Medicare Hospitalization Data
Background: Artificial intelligence (AI) models in healthcare depend on the fidelity of diagnostic data, yet the quality of such data is often compromised by variability in clinical documentation practices. In dementia, a condition already prone to diagnostic ambiguity, this variability may introduce systematic distortion into claims-based research and AI model development. Methods: We analyzed Medicare Part A hospitalization data from 2016-2018 to examine patterns of dementia-related ICD-10 …

Social and Political Framing in Search Engine Results
Amrit Poudel, Tim Weninger
https://arxiv.org/abs/2507.13325 https://arxiv.org/p…

Social and Political Framing in Search Engine Results
Search engines play a crucial role in shaping public discourse by influencing how information is accessed and framed. While prior research has extensively examined various dimensions of search bias -- such as content prioritization, indexical bias, political polarization, and sources of bias -- an important question remains underexplored: how do search engines and ideologically-motivated user queries contribute to bias in search results. This study analyzes the outputs of major search engines u…

Bivariate Distribution Regression; Theory, Estimation and an Application to Intergenerational Mobility
Victor Chernozhukov, Iv\'an Fern\'andez-Val, Jonas Meier, Aico van Vuuren, Francis Vella
https://arxiv.org/abs/2508.12716

Bivariate Distribution Regression; Theory, Estimation and an Application to Intergenerational Mobility
We employ distribution regression (DR) to estimate the joint distribution of two outcome variables conditional on chosen covariates. While Bivariate Distribution Regression (BDR) is useful in a variety of settings, it is particularly valuable when some dependence between the outcomes persists after accounting for the impact of the covariates. Our analysis relies on a result from Chernozhukov et al. (2018) which shows that any conditional joint distribution has a local Gaussian representation. W…

Artificial Intelligence and Civil Discourse: How LLMs Moderate Climate Change Conversations
Wenlu Fan, Wentao Xu
https://arxiv.org/abs/2506.12077 https://

Artificial Intelligence and Civil Discourse: How LLMs Moderate Climate Change Conversations
As large language models (LLMs) become increasingly integrated into online platforms and digital communication spaces, their potential to influence public discourse - particularly in contentious areas like climate change - requires systematic investigation. This study examines how LLMs naturally moderate climate change conversations through their distinct communicative behaviors. We conduct a comparative analysis of conversations between LLMs and human users on social media platforms, using fiv…

Cross-lingual Few-shot Learning for Persian Sentiment Analysis with Incremental Adaptation
Farideh Majidi, Ziaeddin Beheshtifard
https://arxiv.org/abs/2507.11634

Cross-lingual Few-shot Learning for Persian Sentiment Analysis with Incremental Adaptation
This research examines cross-lingual sentiment analysis using few-shot learning and incremental learning methods in Persian. The main objective is to develop a model capable of performing sentiment analysis in Persian using limited data, while getting prior knowledge from high-resource languages. To achieve this, three pre-trained multilingual models (XLM-RoBERTa, mDeBERTa, and DistilBERT) were employed, which were fine-tuned using few-shot and incremental learning approaches on small samples o…