44 research outputs found
IDRE: AI Generated Dataset for Enhancing Empathetic Chatbot Interactions in Italian language
No full textThis paper introduces IDRE (Italian Dataset for Rephrasing with Empathy), a novel automatically generated Italian linguistic dataset. IDRE comprises typical chatbot user utterances in the healthcare domain, corresponding chatbot responses, and empathetically enhanced chatbot responses. The dataset was generated using the Llama2 language model and evaluated by human raters based on predefined metrics. The IDRE dataset offers a comprehensive and realistic collection of Italian chatbot-user interactions suitable for training and refining chatbot models in the healthcare domain. This facilitates the development of chatbots capable of natural and productive conversations with healthcare users. Notably, the dataset incorporates empathetically enhanced chatbot responses, enabling researchers to investigate the effects of empathetic language on fostering more positive and engaging human-machine interactions within healthcare settings. The methodology employed for the construction of the IDRE dataset can be extended to generate phrases in additional languages and domains, thereby expanding its applicability and utility. The IDRE dataset is publicly available for research purposes
The IDRE Dataset in Practice: Training and Evaluation of Small-to-Medium-Sized LLMs for Empathetic Rephrasing
No full textIntegrating emotional intelligence into AI systems is essential for developing empathetic chatbots, yet deploying fully empathetic models is often constrained by business, ethical, and computational factors. We propose an innovative solution: a dedicated empathy rephrasing layer that operates downstream of a chatbot’s initial response. This layer leverages large language models (LLMs) to infuse empathy into the chatbot’s output without altering its core meaning, thereby enhancing emotional intelligence and user engagement. To implement this layer, we extend and validate the IDRE (Italian Dialogue for Empathetic Responses) dataset. We evaluated small- and medium-scale LLMs across three configurations: baseline models, models augmented via few-shot learning with IDRE exemplars, and models fine-tuned on IDRE. Performance was quantitatively assessed using the LLM-as-a-judge paradigm, leveraging custom metrics. These results were further validated through an independent human evaluation and supported by established NLP similarity metrics, ensuring a robust triangulation of findings. Results confirm that both few-shot prompting and fine-tuning with IDRE significantly enhance the models’ capacity for empathetic language generation. Applications include empathetic AI in healthcare, such as virtual assistants for patient support, and demonstrate promising generalization to other domains. All datasets, prompts, fine-tuned models, and scripts are publicly available to ensure transparency and reproducibility
Trajectory phase transitions in non-interacting systems: all-to-all dynamics and the random energy model
No full textData for figures in "Trajectory phase transitions in non-interacting systems: all-to-all dynamics and the random energy model" paper with Chokri Manai and Simone Warze
Financial situation analysis in enterprise SIA "Tavai un Manai veselībai" SIA
No full textBakalaura darba tēma ir „Uzņēmuma SIA „Tavai un Manai veselībai” finanšu stāvokļa analīze”.
Darba mērķis ir uz teorētisko un praktisko materiālu pamata izpētīt un analizēt uzņēmuma SIA „Tavai un Manai veselībai” esošo finansiālo stāvokli, pielietojot dažādas analīzes metodes, veikt secinājumus un priekšlikumus uzņēmuma darbības un finansiālā stāvokļa uzlabošanai.
Darbā ir izanalizēti un aprēķināti: uzņēmuma likviditātes, aktīvu izmantošanas efektivitātes, finansiālā stāvokļa, maksātspējas un rentabilitātes rādītāji.
Bakalaura darbs sastāv no ievada, trīs nodaļām, secinājumiem un priekšlikumiem, kā arī izmantotās literatūras un avotu saraksta.
Lai sasniegtu darba mērķi autore izvirzīja deviņus uzdevumus. Darba apjoms ir 92 lappuses, tajās iekļauti 22 attēli, 25 tabulas, 22 formulas un 9 pielikumi. Bibliogrāfiskajā sarakstā izmantoti 27 literatūras saraksti.
Atslēgvārdi: apgrozāmie līdzekļi, pašu kapitāls, likviditāte, maksātspēja, rentabilitāte.The theme of diploma paper is „Financial situation analysis in enterprise „Tavai un Manai veselībai” SIA”.
The aim of the paper is to investigate the existing financial position at enterprise basing the analysis on the theoretical and practical materials and using different methods of financial analysis, and drawing out conclusions and making suggestions in order to improve the activity of the enterprise.
The following data are analyzed, calculated and estimated in the paper: the ratios of liquidity, efficiency of the activity, financial stability, solvency and profitability.
The diploma paper consists of introduction, three chapters, conclusion, suggestions, the list of bibliography and sources are used in it.
To reach the aim of the papper, the author has set 9 tasks. The amount of the paper is 92 pages with 22 pictures, 25 tables, 22 formulas and 9 appendices are added. 27 sources of bibliography are used.
Keywords: working capital, equity capital, liquidity, solvency, profitabilit
Dimethyl Fumarate and Intestine: From Main Suspect to Potential Ally against Gut Disorders
No full textDimethyl fumarate (DMF) is a well-characterized molecule that exhibits immuno-modulatory, anti-inflammatory, and antioxidant properties and that is currently approved for the treatment of psoriasis and multiple sclerosis. Due to its Nrf2-dependent and independent mechanisms of action, DMF has a therapeutic potential much broader than expected. In this comprehensive review, we discuss the state-of-the-art and future perspectives regarding the potential repurposing of DMF in the context of chronic inflammatory diseases of the intestine, such as inflammatory bowel disorders (i.e., Crohn's disease and ulcerative colitis) and celiac disease. DMF's mechanisms of action, as well as an exhaustive analysis of the in vitro/in vivo evidence of its beneficial effects on the intestine and the gut microbiota, together with observational studies on multiple sclerosis patients, are here reported. Based on the collected evidence, we highlight the new potential applications of this molecule in the context of inflammatory and immune-mediated intestinal diseases
Generalized Random Energy Models in a Transversal Magnetic Field: Free Energy and Phase Diagrams
No full textWe determine explicit variational expressions for the free energy of
mean-field spin glasses in a transversal magnetic field, whose glass
interaction is given by a hierarchical Gaussian potential as in Derrida's
Generalized Random Energy Model (GREM), its continuous version (CREM) or the
non-hierarchical GREM. The corresponding phase diagrams, which generally
include glass transitions as well as magnetic transitions, are discussed. In
the glass phase, the free energy is generally determined by both the parameters
of the classical model and the transversal field
A Parisi Formula for Quantum Spin Glasses
No full textWe establish three equivalent versions of a Parisi formula for the free
energy of mean-field spin glasses in a transversal magnetic field. These
results are derived from available results for classical vector spin glasses by
an approximation method using the functional integral representation of the
partition function. In this approach, the order parameter is a non-decreasing
function with values in the non-negative, real hermitian Hilbert-Schmidt
operators. For the quantum Sherrington-Kirkpatrick model, we also show that
under the assumption of self-averaging of the self-overlap, the optimising
Parisi order parameter is found within a two-dimensional subspace spanned by
the self-overlap and the fully stationary overlap
Spectral Analysis of the Quantum Random Energy Model
No full textThe Quantum Random Energy Model (QREM) is a random matrix of Anderson-type
which describes effects of a transversal magnetic field on Derrida's spin
glass. The model exhibits a glass phase as well as a classical and a quantum
paramagnetic phase. We analyze in detail the low-energy spectrum and establish
a localization-delocalization transition for the corresponding eigenvectors of
the QREM. Based on a combination of random matrix and operator techniques as
well as insights in the random geometry, we derive next-to-leading order
asymptotics for the ground-state energy and eigenvectors in all regimes of the
parameter space. Based on this, we also deduce the next-to-leading order of the
free energy, which turns out to be deterministic and on order one in the system
size in all phases of the QREM. As a result, we determine the nature of the
fluctuations of the free energy in the spin glass regime.Comment: Typos and presentation corrected, refernces adde
The Spectral Gap and Low-Energy Spectrum in Mean-Field Quantum Spin Systems
No full textA semiclassical analysis based on spin-coherent states is used to establish a classification and novel simple formulae for the spectral gap of mean-field spin Hamiltonians. For gapped systems, we provide a full description of the low-energy spectra based on a second-order approximation to the semiclassical Hamiltonian, hence justifying fluctuation theory at zero temperature for this case. We also point out a shift caused by the spherical geometry in these second-order approximations
Trajectory phase transitions in non-interacting systems: all-to-all dynamics and the random energy model
No full textWe study the fluctuations of time-additive random observables in the
stochastic dynamics of a system of non-interacting Ising spins. We mainly
consider the case of all-to-all dynamics where transitions are possible between
any two spin configurations with uniform rates. We show that the cumulant
generating function of the time-integral of a normally distributed quenched
random function of configurations, i.e., the energy function of the random
energy model (REM), has a phase transition in the large limit for
trajectories of any time extent. We prove this by determining the exact limit
of the scaled cumulant generating function. This is accomplished by connecting
the dynamical problem to a spectral analysis of the all-to-all quantum REM. We
also discuss finite corrections as observed in numerical simulations
