BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Jacopo Staiano

Jacopo Staiano appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Computation and Languagecs.CYphysics.soc-phSocial and Information NetworksMachine LearningArtificial IntelligenceComputer VisionHuman-Computer InteractionMultimedia

Catalog footprint

What is connected

16works
9topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

16 published item(s)

preprint2026arXiv

Human-LLM Dialogue Improves Diagnostic Accuracy in Emergency Care

Clinical decision-making in emergency medicine demands rapid, accurate diagnoses under uncertainty. Despite benchmark progress, evidence for LLMs as interactive aids in live physician workflows remains sparse. MedSyn lets physicians iteratively query an LLM provided with the full clinical record while initially viewing only the chief complaint. Seven physicians (three seniors, four residents) completed baseline and AI-assisted sessions across 52 MIMIC-IV cases stratified by difficulty. Blinded evaluation showed residents' Hard-case correctness rose from 0.589 to 0.734; difficulty-standardised completely-correct rates confirmed a medium effect (Δ = 0.092; p = 0.071; d = 0.47). Automated metrics corroborated these gains: standardised any-match accuracy improved by 0.156 (p < 0.0001), and residents showed the largest F1 gain (Δ = 0.138; p < 0.0001). Dialogue analysis revealed expertise-dependent strategies (seniors asked targeted, hypothesis-driven questions; residents relied on broader queries) and cross-expertise concordance increased (Δ = 0.145; p < 0.0001). Interactive LLM support meaningfully enhances diagnostic reasoning.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

KoRe: Compact Knowledge Representations for Large Language Models

Modern Large Language Models (LLMs) have shown impressive performances in user-facing tasks such as question answering, as well as consistent improvements in reasoning capabilities. Still, the way these models encode knowledge seems inherently flawed: by design, LLMs encode world-knowledge within their parameters. This way of representing knowledge is inherently opaque, difficult to debug and update, and prone to hallucinations. On the other hand, Knowledge Graphs can provide human-readable and easily editable world knowledge representations, and their application in knowledge-intensive tasks has consistently proven beneficial to downstream performance. Nonetheless, current integration techniques require extensive retraining or finetuning. To overcome this issue, we introduce KoRe, a methodology to encode 1-hop sub-graphs into compact discrete knowledge tokens and inject them into a LLM backbone. We test the proposed approach on three established benchmarks, and report competitive performances coupled with a significant reduction (up to 10x) in token usage. Our results show that compact discrete KG representations can efficiently and effectively be used to ground modern LLMs.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Generative Cooperative Networks for Natural Language Generation

Generative Adversarial Networks (GANs) have known a tremendous success for many continuous generation tasks, especially in the field of image generation. However, for discrete outputs such as language, optimizing GANs remains an open problem with many instabilities, as no gradient can be properly back-propagated from the discriminator output to the generator parameters. An alternative is to learn the generator network via reinforcement learning, using the discriminator signal as a reward, but such a technique suffers from moving rewards and vanishing gradient problems. Finally, it often falls short compared to direct maximum-likelihood approaches. In this paper, we introduce Generative Cooperative Networks, in which the discriminator architecture is cooperatively used along with the generation policy to output samples of realistic texts for the task at hand. We give theoretical guarantees of convergence for our approach, and study various efficient decoding schemes to empirically achieve state-of-the-art results in two main NLG tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Which Discriminator for Cooperative Text Generation?

Language models generate texts by successively predicting probability distributions for next tokens given past ones. A growing field of interest tries to leverage external information in the decoding process so that the generated texts have desired properties, such as being more natural, non toxic, faithful, or having a specific writing style. A solution is to use a classifier at each generation step, resulting in a cooperative environment where the classifier guides the decoding of the language model distribution towards relevant texts for the task at hand. In this paper, we examine three families of (transformer-based) discriminators for this specific task of cooperative decoding: bidirectional, left-to-right and generative ones. We evaluate the pros and cons of these different types of discriminators for cooperative generation, exploring respective accuracy on classification tasks along with their impact on the resulting sample quality and computational performances. We also provide the code of a batched implementation of the powerful cooperative decoding strategy used for our experiments, the Monte Carlo Tree Search, working with each discriminator for Natural Language Generation.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

ColdGANs: Taming Language GANs with Cautious Sampling Strategies

Training regimes based on Maximum Likelihood Estimation (MLE) suffer from known limitations, often leading to poorly generated text sequences. At the root of these limitations is the mismatch between training and inference, i.e. the so-called exposure bias, exacerbated by considering only the reference texts as correct, while in practice several alternative formulations could be as good. Generative Adversarial Networks (GANs) can mitigate those limitations but the discrete nature of text has hindered their application to language generation: the approaches proposed so far, based on Reinforcement Learning, have been shown to underperform MLE. Departing from previous works, we analyze the exploration step in GANs applied to text generation, and show how classical sampling results in unstable training. We propose to consider alternative exploration strategies in a GAN framework that we name ColdGANs, where we force the sampling to be close to the distribution modes to get smoother learning dynamics. For the first time, to the best of our knowledge, the proposed language GANs compare favorably to MLE, and obtain improvements over the state-of-the-art on three generative tasks, namely unconditional text generation, question generation, and abstractive summarization.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Discriminative Adversarial Search for Abstractive Summarization

We introduce a novel approach for sequence decoding, Discriminative Adversarial Search (DAS), which has the desirable properties of alleviating the effects of exposure bias without requiring external metrics. Inspired by Generative Adversarial Networks (GANs), wherein a discriminator is used to improve the generator, our method differs from GANs in that the generator parameters are not updated at training time and the discriminator is only used to drive sequence generation at inference time. We investigate the effectiveness of the proposed approach on the task of Abstractive Summarization: the results obtained show that a naive application of DAS improves over the state-of-the-art methods, with further gains obtained via discriminator retraining. Moreover, we show how DAS can be effective for cross-domain adaptation. Finally, all results reported are obtained without additional rule-based filtering strategies, commonly used by the best performing systems available: this indicates that DAS can effectively be deployed without relying on post-hoc modifications of the generated outputs.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

MLSUM: The Multilingual Summarization Corpus

We present MLSUM, the first large-scale MultiLingual SUMmarization dataset. Obtained from online newspapers, it contains 1.5M+ article/summary pairs in five different languages -- namely, French, German, Spanish, Russian, Turkish. Together with English newspapers from the popular CNN/Daily mail dataset, the collected data form a large scale multilingual dataset which can enable new research directions for the text summarization community. We report cross-lingual comparative analyses based on state-of-the-art systems. These highlight existing biases which motivate the use of a multi-lingual dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Project PIAF: Building a Native French Question-Answering Dataset

Motivated by the lack of data for non-English languages, in particular for the evaluation of downstream tasks such as Question Answering, we present a participatory effort to collect a native French Question Answering Dataset. Furthermore, we describe and publicly release the annotation tool developed for our collection effort, along with the data obtained and preliminary baselines.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

The Death and Life of Great Italian Cities: A Mobile Phone Data Perspective

The Death and Life of Great American Cities was written in 1961 and is now one of the most influential book in city planning. In it, Jane Jacobs proposed four conditions that promote life in a city. However, these conditions have not been empirically tested until recently. This is mainly because it is hard to collect data about "city life". The city of Seoul recently collected pedestrian activity through surveys at an unprecedented scale, with an effort spanning more than a decade, allowing researchers to conduct the first study successfully testing Jacobs's conditions. In this paper, we identify a valuable alternative to the lengthy and costly collection of activity survey data: mobile phone data. We extract human activity from such data, collect land use and socio-demographic information from the Italian Census and Open Street Map, and test the four conditions in six Italian cities. Although these cities are very different from the places for which Jacobs's conditions were spelled out (i.e., great American cities) and from the places in which they were recently tested (i.e., the Asian city of Seoul), we find those conditions to be indeed associated with urban life in Italy as well. Our methodology promises to have a great impact on urban studies, not least because, if replicated, it will make it possible to test Jacobs's theories at scale.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

The Tyranny of Data? The Bright and Dark Sides of Data-Driven Decision-Making for Social Good

The unprecedented availability of large-scale human behavioral data is profoundly changing the world we live in. Researchers, companies, governments, financial institutions, non-governmental organizations and also citizen groups are actively experimenting, innovating and adapting algorithmic decision-making tools to understand global patterns of human behavior and provide decision support to tackle problems of societal importance. In this chapter, we focus our attention on social good decision-making algorithms, that is algorithms strongly influencing decision-making and resource optimization of public goods, such as public health, safety, access to finance and fair employment. Through an analysis of specific use cases and approaches, we highlight both the positive opportunities that are created through data-driven algorithmic decision-making, and the potential negative consequences that practitioners should be aware of and address in order to truly realize the potential of this emergent field. We elaborate on the need for these algorithms to provide transparency and accountability, preserve privacy and be tested and evaluated in context, by means of living lab approaches involving citizens. Finally, we turn to the requirements which would make it possible to leverage the predictive power of data-driven human behavior analysis while ensuring transparency, accountability, and civic participation.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Deep Feelings: A Massive Cross-Lingual Study on the Relation between Emotions and Virality

This article provides a comprehensive investigation on the relations between virality of news articles and the emotions they are found to evoke. Virality, in our view, is a phenomenon with many facets, i.e. under this generic term several different effects of persuasive communication are comprised. By exploiting a high-coverage and bilingual corpus of documents containing metrics of their spread on social networks as well as a massive affective annotation provided by readers, we present a thorough analysis of the interplay between evoked emotions and viral facets. We highlight and discuss our findings in light of a cross-lingual approach: while we discover differences in evoked emotions and corresponding viral effects, we provide preliminary evidence of a generalized explanatory model rooted in the deep structure of emotions: the Valence-Arousal-Dominance (VAD) circumplex. We find that viral facets appear to be consistently affected by particular VAD configurations, and these configurations indicate a clear connection with distinct phenomena underlying persuasive communication.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

SALSA: A Novel Dataset for Multimodal Group Behavior Analysis

Studying free-standing conversational groups (FCGs) in unstructured social settings (e.g., cocktail party ) is gratifying due to the wealth of information available at the group (mining social networks) and individual (recognizing native behavioral and personality traits) levels. However, analyzing social scenes involving FCGs is also highly challenging due to the difficulty in extracting behavioral cues such as target locations, their speaking activity and head/body pose due to crowdedness and presence of extreme occlusions. To this end, we propose SALSA, a novel dataset facilitating multimodal and Synergetic sociAL Scene Analysis, and make two main contributions to research on automated social interaction analysis: (1) SALSA records social interactions among 18 participants in a natural, indoor environment for over 60 minutes, under the poster presentation and cocktail party contexts presenting difficulties in the form of low-resolution images, lighting variations, numerous occlusions, reverberations and interfering sound sources; (2) To alleviate these problems we facilitate multimodal analysis by recording the social interplay using four static surveillance cameras and sociometric badges worn by each participant, comprising the microphone, accelerometer, bluetooth and infrared sensors. In addition to raw data, we also provide annotations concerning individuals' personality as well as their position, head, body orientation and F-formation information over the entire event duration. Through extensive experiments with state-of-the-art approaches, we show (a) the limitations of current methods and (b) how the recorded multiple cues synergetically aid automatic analysis of social interactions. SALSA is available at http://tev.fbk.eu/salsa.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

DepecheMood: a Lexicon for Emotion Analysis from Crowd-Annotated News

While many lexica annotated with words polarity are available for sentiment analysis, very few tackle the harder task of emotion analysis and are usually quite limited in coverage. In this paper, we present a novel approach for extracting - in a totally automated way - a high-coverage and high-precision lexicon of roughly 37 thousand terms annotated with emotion scores, called DepecheMood. Our approach exploits in an original way 'crowd-sourced' affective annotation implicitly provided by readers of news articles from rappler.com. By providing new state-of-the-art performances in unsupervised settings for regression and classification tasks, even using a na\"ıve approach, our experiments show the beneficial impact of harvesting social media data for affective lexicon building.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Money Walks: A Human-Centric Study on the Economics of Personal Mobile Data

In the context of a myriad of mobile apps which collect personally identifiable information (PII) and a prospective market place of personal data, we investigate a user-centric monetary valuation of mobile PII. During a 6-week long user study in a living lab deployment with 60 participants, we collected their daily valuations of 4 categories of mobile PII (communication, e.g. phonecalls made/received, applications, e.g. time spent on different apps, location and media, photos taken) at three levels of complexity (individual data points, aggregated statistics and processed, i.e. meaningful interpretations of the data). In order to obtain honest valuations, we employ a reverse second price auction mechanism. Our findings show that the most sensitive and valued category of personal information is location. We report statistically significant associations between actual mobile usage, personal dispositions, and bidding behavior. Finally, we outline key implications for the design of mobile services and future markets of personal data.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Once Upon a Crime: Towards Crime Prediction from Demographics and Mobile Data

In this paper, we present a novel approach to predict crime in a geographic space from multiple data sources, in particular mobile phone and demographic data. The main contribution of the proposed approach lies in using aggregated and anonymized human behavioral data derived from mobile network activity to tackle the crime prediction problem. While previous research efforts have used either background historical knowledge or offenders' profiling, our findings support the hypothesis that aggregated human behavioral data captured from the mobile network infrastructure, in combination with basic demographic information, can be used to predict crime. In our experimental results with real crime data from London we obtain an accuracy of almost 70% when predicting whether a specific area in the city will be a crime hotspot or not. Moreover, we provide a discussion of the implications of our findings for data-driven crime analysis.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Exploring Image Virality in Google Plus

Reactions to posts in an online social network show different dynamics depending on several textual features of the corresponding content. Do similar dynamics exist when images are posted? Exploiting a novel dataset of posts, gathered from the most popular Google+ users, we try to give an answer to such a question. We describe several virality phenomena that emerge when taking into account visual characteristics of images (such as orientation, mean saturation, etc.). We also provide hypotheses and potential explanations for the dynamics behind them, and include cases for which common-sense expectations do not hold true in our experiments.

0 citations0 reviewsNo code linkedOpen access