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.
LLM evaluation suffers from systematic biases and lacks reliable positive judgments.
This research explores inductive biases for deep learning to improve AI's higher-level cognition.
Study models human investors' sub-rational behavior in financial markets.
Experiment shows cognitive biases impact human-AI collaboration, highlighting the need for diverse evaluator samples.
Machine learning algorithms are now frequently used in sensitive contexts that substantially affect the course of human lives, such as credit lending or criminal justice. This is driven by the idea that `objective' machines base their decisions solely on facts and remain unaffected by human cognitive biases, discrimina…
Bayesian models explain human time perception biases.
New technique reduces language biases in large language models.
Paper tackles unobserved confounding in human-AI collaborations.
Large neural models have demonstrated human-level performance on language and vision benchmarks, while their performance degrades considerably on adversarial or out-of-distribution samples. This raises the question of whether these models have learned to solve a dataset rather than the underlying task by overfitting to…
While the interpretability of machine learning models is often equated with their mere syntactic comprehensibility, we think that interpretability goes beyond that, and that human interpretability should also be investigated from the point of view of cognitive science. The goal of this paper is to discuss to what exten…
Improved speech enhancement with larger neural networks using novel embeddings and biases.
Accurately predicting the outcome of sporting events has been a goal for many groups who seek to maximize profit. What makes this challenging is that the outcome of an event can be influenced by many factors that dynamically change across time. Oddsmakers attempt to estimate these factors by using both algorithmic and …
Algorithm reduces audit costs by identifying best service configurations from biased textual evidence.
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…
Our goal is for agents to optimize the right reward function, despite how difficult it is for us to specify what that is. Inverse Reinforcement Learning (IRL) enables us to infer reward functions from demonstrations, but it usually assumes that the expert is noisily optimal. Real people, on the other hand, often have s…
Develops methods to correct bias in AI feedback for more accurate alignment.
Method trains a debiased model from a biased one by focusing on samples that contradict the bias.
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…
Framework assesses autograders' reliability and biases.
Study finds gender bias in human evaluators and shows how machine learning can mitigate it.
RAFT fine-tunes models using high-quality samples to align them with human preferences.
Algorithm identifies best arm with biased proxy and selective ground truth audits.
Study shows how algorithmic prediction affects US housing market, reducing racial wealth disparities.
LLMs overestimate stock returns and are less accurate at predicting extreme outcomes.
Study reveals biases in ImageNet models are not sufficient for generalization.
Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes. Some recent studies suggest a more important role of image textures. We here put these conflicting hypotheses to a quantitative test by evaluating CNNs and human observers on…
We evaluate the folk wisdom that algorithmic decision rules trained on data produced by biased human decision-makers necessarily reflect this bias. We consider a setting where training labels are only generated if a biased decision-maker takes a particular action, and so "biased" training data arise due to discriminato…
Proposes a new fairness definition based on equity for machine learning classification.
Interview study reveals considerations for designing semi-automated bias detection tools.
Improves accuracy and fairness in prediction systems with multiple domain experts.
Mitigates biases in reward models using variational inference.
Human irrationality can improve AI design, study shows.
Sparse linear models improve neural network debuggability.
Embodied cognition states that semantics is encoded in the brain as firing patterns of neural circuits, which are learned according to the statistical structure of human multimodal experience. However, each human brain is idiosyncratically biased, according to its subjective experience history, making this biological s…
Integrates inductive biases into VAEs using intermediary latent variables.
Paper proposes a data augmentation method for LLM-generated data in market research.
The influence of human judgement is ubiquitous in datasets used across the analytics industry, yet humans are known to be sub-optimal decision makers prone to various biases. Analysing biased datasets then leads to biased outcomes of the analysis. Bias by protected characteristics (e.g. race) is of particular interest …
Bias is known to be an impediment to fair decisions in many domains such as human resources, the public sector, health care etc. Recently, hope has been expressed that the use of machine learning methods for taking such decisions would diminish or even resolve the problem. At the same time, machine learning experts war…
ConvNets and Imagenet have driven the recent success of deep learning for image classification. However, the marked slowdown in performance improvement combined with the lack of robustness of neural networks to adversarial examples and their tendency to exhibit undesirable biases question the reliability of these metho…
Optimal allocation of human effort to correct AI assessments in decision-making.
Improved NTL detection using human-in-the-loop approach with explainability.
What we discover and see online, and consequently our opinions and decisions, are becoming increasingly affected by automated machine learned predictions. Similarly, the predictive accuracy of learning machines heavily depends on the feedback data that we provide them. This mutual influence can lead to closed-loop inte…
Human decision-making underlies all economic behavior. For the past four decades, human decision-making under uncertainty has continued to be explained by theoretical models based on prospect theory, a framework that was awarded the Nobel Prize in Economic Sciences. However, theoretical models of this kind have develop…
Drawing an inspiration from behavioral studies of human decision making, we propose here a more general and flexible parametric framework for reinforcement learning that extends standard Q-learning to a two-stream model for processing positive and negative rewards, and allows to incorporate a wide range of reward-proce…
In many machine learning applications, there are multiple decision-makers involved, both automated and human. The interaction between these agents often goes unaddressed in algorithmic development. In this work, we explore a simple version of this interaction with a two-stage framework containing an automated model and…
AI bias arises from human-defined goals, not algorithmic flaws.
The use of synthetic data generated by Generative Adversarial Networks (GANs) has become quite a popular method to do data augmentation for many applications. While practitioners celebrate this as an economical way to get more synthetic data that can be used to train downstream classifiers, it is not clear that they re…
Recent developments in Neural Relation Extraction (NRE) have made significant strides towards Automated Knowledge Base Construction (AKBC). While much attention has been dedicated towards improvements in accuracy, there have been no attempts in the literature to our knowledge to evaluate social biases in NRE systems. W…