A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Enhances preference learning by incorporating response times into binary choices.
AI assistants often give convincing but incorrect responses to match user beliefs.
Recent studies in the field of human vision science suggest that the human responses to the stimuli on a visual display are non-deterministic. People may attend to different locations on the same visual input at the same time. Based on this knowledge, we propose a new stochastic model of visual attention by introducing…
Digital personas improve survey results for stable attributes but fail for subjective responses.
New method for explaining dialogue response generation models.
In this study we present a kernel based convolution model to characterize neural responses to natural sounds by decoding their time-varying acoustic features. The model allows to decode natural sounds from high-dimensional neural recordings, such as magnetoencephalography (MEG), that track timing and location of human …
Response time improves alignment with diverse human preferences.
The paper enhances preference learning by incorporating response time data.
Framework for responsible LLM deployment with human involvement and decentralized technologies.
We aim to reduce the burden of programming and deploying autonomous systems to work in concert with people in time-critical domains, such as military field operations and disaster response. Deployment plans for these operations are frequently negotiated on-the-fly by teams of human planners. A human operator then trans…
Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions. However, exactly what kinds of explanation are truly human-interpretable remains poorly understood. This work advances our understanding of what makes explanations …
Item Response Theory (IRT) is a ubiquitous model for understanding humans based on their responses to questions, used in fields as diverse as education, medicine and psychology. Large modern datasets offer opportunities to capture more nuances in human behavior, potentially improving test scoring and better informing p…
Paper explores limits and possibilities of aligning LLMs with human preferences.
Monitoring physiological responses to hemodynamic stress can help in determining appropriate treatment and ensuring good patient outcomes. Physicians' intuition suggests that the human body has a number of physiological response patterns to hemorrhage which escalate as blood loss continues, however the exact etiology a…
Automates U.S. visa petition document classification and RFE response generation.
We proposed a probabilistic approach to joint modeling of participants' reliability and humans' regularity in crowdsourced affective studies. Reliability measures how likely a subject will respond to a question seriously; and regularity measures how often a human will agree with other seriously-entered responses coming…
Paper proposes a robust RLHF algorithm for LLMs, improving response preference over baselines.
GraphKKE learns fixed-length feature vectors from time-evolving graphs of human microbiome data.
In this paper, we present an experimental study for the classification of perceived human stress using non-invasive physiological signals. These include electroencephalography (EEG), galvanic skin response (GSR), and photoplethysmography (PPG). We conducted experiments consisting of steps including data acquisition, fe…
Computer simulations have become a popular tool of assessing complex skills such as problem-solving skills. Log files of computer-based items record the entire human-computer interactive processes for each respondent. The response processes are very diverse, noisy, and of nonstandard formats. Few generic methods have b…
New algorithm speeds up IRT model fitting for large datasets.
Model predicts anti-cancer drug responses using gene and molecular data.
Improved antibody humanness prediction using patent data.
Designs algorithms to assist humans without affecting their decisions.
A new uncertainty principle helps traders better understand market activity.
Automated scoring engines are increasingly being used to score the free-form text responses that students give to questions. Such engines are not designed to appropriately deal with responses that a human reader would find alarming such as those that indicate an intention to self-harm or harm others, responses that all…
Bayesian nonparametric models, such as Gaussian processes, provide a compelling framework for automatic statistical modelling: these models have a high degree of flexibility, and automatically calibrated complexity. However, automating human expertise remains elusive; for example, Gaussian processes with standard kerne…
Conformal prediction sets improve human decision making by quantifying model uncertainty.
Deep learning model classifies concurrent human interactions from WiFi data with high accuracy.
Study evaluates new models using human feedback from another model.
How to generate human like response is one of the most challenging tasks for artificial intelligence. In a real application, after reading the same post different people might write responses with positive or negative sentiment according to their own experiences and attitudes. To simulate this procedure, we propose a s…
Access to high-quality education at scale is limited by the difficulty of providing student feedback on open-ended assignments in structured domains like computer programming, graphics, and short response questions. This problem has proven to be exceptionally difficult: for humans, it requires large amounts of manual w…
The effectiveness of machine learning algorithms depends on the quality and amount of data and the operationalization and interpretation by the human analyst. In humanitarian response, data is often lacking or overburdening, thus ambiguous, and the time-scarce, volatile, insecure environments of humanitarian activities…
Tactile enhanced multimedia is generated by synchronizing traditional multimedia clips, to generate hot and cold air effect, with an electric heater and a fan. This objective is to give viewers a more realistic and immersing feel of the multimedia content. The response to this enhanced multimedia content (mulsemedia) i…
Human-AI teaming suffers from calibration issues.
PILAF optimizes reward models from human feedback for better policy alignment.
Unified framework to bridge human and LLM judgments.
Rapid intensification (RI) of tropical cyclones often causes major destruction to human civilization due to short response time. It is an important yet challenging task to accurately predict this kind of extreme weather event in advance. Traditionally, meteorologists tackle the task with human-driven feature extraction…
For a safe, natural and effective human-robot social interaction, it is essential to develop a system that allows a robot to demonstrate the perceivable responsive behaviors to complex human behaviors. We introduce the Multimodal Deep Attention Recurrent Q-Network using which the robot exhibits human-like social intera…
LLMs can predict CFO responses to economic surveys
Motivation: Cell-biological processes are regulated through a complex network of interactions between genes and their products. The processes, their activating conditions, and the associated transcriptional responses are often unknown. Organism-wide modeling of network activation can reveal unique and shared mechanisms…
Human decision-makers often receive assistance from data-driven algorithmic systems that provide a score for evaluating objects, including individuals. The scores are generated by a function (mechanism) that takes a set of features as input and generates a score.The scoring functions are either machine-learned or human…
The Knowledge Base (KB) used for real-world applications, such as booking a movie or restaurant reservation, keeps changing over time. End-to-end neural networks trained for these task-oriented dialogs are expected to be immune to any changes in the KB. However, existing approaches breakdown when asked to handle such c…
Study on model accuracy when human subjects adapt to predictions.
We propose an adversarial learning approach for generating multi-turn dialogue responses. Our proposed framework, hredGAN, is based on conditional generative adversarial networks (GANs). The GAN's generator is a modified hierarchical recurrent encoder-decoder network (HRED) and the discriminator is a word-level bidirec…
We propose a novel dialogue modeling framework, the first-ever nonparametric kernel functions based approach for dialogue modeling, which learns kernelized hashcodes as compressed text representations; unlike traditional deep learning models, it handles well relatively small datasets, while also scaling to large ones. …
New RLHF approach mitigates bias in aligning LLMs with human preferences.
AI-Trader benchmarks LLMs in live financial markets, revealing poor trading performance.