LLM evaluation suffers from systematic biases and lacks reliable positive judgments.
problem LLM evaluation suffers from systematic biases and lacks reliable positive judgments.
method Formulate LLM evaluation as a positive-unlabelled learning problem and propose a geometric auditing framework based on Partial Optimal Transport.
result Improved alignment with human preferences, increased robustness to presentation biases, and interpretable confidence estimates.
This research explores inductive biases for deep learning to improve AI's higher-level cognition.
problem Current AI struggles with flexible out-of-distribution and systematic generalization.
method Examines and proposes new inductive biases for deep learning.
result Identifies specific inductive biases for higher-level sequential processing.
Study models human investors' sub-rational behavior in financial markets.
problem Lack of a comprehensive model for human sub-rationality in financial markets.
method Flexible reinforcement learning model incorporating five human sub-rational aspects.
result Model accurately reproduces human behavior and reveals insights into market dynamics.
Experiment shows cognitive biases impact human-AI collaboration, highlighting the need for diverse evaluator samples.
problem Cognitive biases affect human-AI collaboration, leading to suboptimal outcomes.
method Randomized experiment with 2,784 participants, manipulating AI suggestion quality, task burden, and financial incentives.
result Individual attitudes toward AI are the strongest predictor of performance, influencing accuracy and overcorrection.
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.
problem Understanding human time perception using Bayesian inference.
method Agent-based machine learning models and empirical data analysis.
result Bayesian models can replicate human time estimation biases.
New technique reduces language biases in large language models.
problem Gap between language and thought in large language models.
method Proposes Language-of-Thoughts (LoT) technique to adjust order and tokens.
result Significantly reduces language biases and improves reasoning tasks.
Paper tackles unobserved confounding in human-AI collaborations.
problem Unobserved confounding undermines human-AI collaboration effectiveness.
method Combines sensitivity analysis from causal inference with AI-driven statistical modeling.
result Enhances robustness and reliability of collaborative outcomes.
AFLite filters dataset biases to improve model generalization.
problem Overfitting to dataset biases degrades model performance on out-of-distribution samples.
method AFLite adversarially filters dataset biases, reducing their impact on model performance.
result Filtered datasets yield better generalization to out-of-distribution tasks.
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.
problem Decreased robustness of speech enhancement models to real-world use cases.
method Frequency-positional embeddings, semi-supervised training, biased loss function.
result Better performance on real recordings with improved large neural network architecture.
The paper investigates how ambiguous data and cognitive biases affect machine learning in humanitarian decision making.
problem Ambiguous data and cognitive biases impact the interpretability of machine learning models in humanitarian decision making.
method The study will explore the effects of data ambiguity and cognitive biases on machine learning algorithms in humanitarian contexts.
result The research aims to uncover the specific ways in which ambiguous data and cognitive biases influence the interpretability of machine learning models in humanitarian decision making.
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.
problem Designing service systems from textual evidence requires accurate selection despite biased automated scoring.
method Developed PP-LUCB algorithm combining LLM scores and selective audits to minimize costs.
result Correctly identified the best model in 40/40 trials with 90% cost reduction.
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.
problem Systematic bias in AI feedback compared to human labels.
method Two debiased alignment methods: DDPO and DIPO.
result Methods improve alignment efficiency and performance close to human-labeled data.
Method trains a debiased model from a biased one by focusing on samples that contradict the bias.
problem Training neural networks can lead to biased predictions due to spurious correlations.
method Train a pair of neural networks, intentionally biasing one and debiasing the other by focusing on contradictory samples.
result Our method significantly improves training against various types of biases, sometimes outperforming explicit supervision methods.
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.
problem Mixed reliability and biases in autograders for LLM evaluation.
method Bayesian GLMs to model evaluation outcomes.
result Explicit quantification of scoring differences and biases.
Study examines whether biased training data lead to biased algorithms.
problem Tackles the issue of bias in algorithmic decision-making.
method Examines a setting where biased human decision-makers affect training data and labels.
result Clarifies conditions for bias reversal in algorithmic decision rules.
Study finds gender bias in human evaluators and shows how machine learning can mitigate it.
problem Gender bias in human decision-making on micro-lending platforms.
method Structural econometric model and machine learning algorithms trained on real-world data.
result Machine learning algorithms can mitigate both preference-based and belief-based biases.
RAFT fine-tunes models using high-quality samples to align them with human preferences.
problem Aligning generative models with human ethics and preferences.
method RAFT selects high-quality samples, discards undesired behavior, and fine-tunes the model on filtered samples.
result RAFT improves model performance in reward learning and automated metrics.
Algorithm identifies best arm with biased proxy and selective ground truth audits.
problem Fixed-confidence best-arm identification with biased proxy and selective ground truth.
method Propensity-weighted estimator and adaptive auditing algorithm.
result Plug-in Neyman rule achieves near-oracle audit efficiency.
Study shows how algorithmic prediction affects US housing market, reducing racial wealth disparities.
problem Impact of algorithmic prediction on housing market and racial wealth disparities.
method Natural experiment using digitization of housing records to study entry, allocation, and prices.
result Digitization leads to increased sale prices for minority-owned homes, reducing racial wealth disparities.
LLMs overestimate stock returns and are less accurate at predicting extreme outcomes.
problem Behavioral biases in LLMs' stock return forecasts.
method Comparison of LLM forecasts with crowd-sourced estimates and historical data.
result LLMs overestimate stock returns and are less accurate at predicting extreme outcomes.
Study reveals biases in ImageNet models are not sufficient for generalization.
problem Understanding and improving generalization of image classification models.
method Large-scale study of 48 ImageNet models trained via various methods.
result Biases identified in ImageNet models do not fully explain 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…
Proposes a new fairness definition based on equity for machine learning classification.
problem Machine learning systems can perpetuate societal biases.
method Formalizes a new fairness definition based on equity, operationalizes it for classification, and evaluates its effectiveness.
result Demonstrates the effectiveness of the new fairness definition for equitable classification.
Interview study reveals considerations for designing semi-automated bias detection tools.
problem Detecting and mitigating machine learning biases.
method Interview study with 11 machine learning practitioners.
result Four considerations identified for tool design.
Improves accuracy and fairness in prediction systems with multiple domain experts.
problem Designing unbiased and accurate deferral systems with multiple experts.
method Proposes a framework for learning a classifier and deferral system that chooses to defer to multiple human experts.
result Significantly improves accuracy and fairness of final predictions compared to baselines.
Mitigates biases in reward models using variational inference.
problem Spurious correlations in reward models that align large language models with human preferences.
method Formulates data-generating process, identifies non-spurious latent variables, and uses variational inference to recover them.
result Effective mitigation of spurious correlation issues, yielding more robust reward models.
Human irrationality can improve AI design, study shows.
problem Improving AI by learning from human decision-making biases.
method Developed a novel POMDP model to simulate human decision-making in contextual choice tasks.
result Reinforcement learners can exploit human irrationalities to make better decisions.
Sparse linear models improve neural network debuggability.
problem Improving neural network interpretability and debugging.
method Using sparse linear models over learned deep feature representations.
result The approach leads to more debuggable and accurate neural networks.
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.
problem Ineffective mechanisms for incorporating inductive biases into VAEs.
method InteL-VAEs use an intermediary latent space to control encoding, with a parametric function to enforce desired properties.
result InteL-VAEs lead to better generative models and representations.
Paper proposes a data augmentation method for LLM-generated data in market research.
problem Bias in LLM-generated data in market research.
method Statistical data augmentation approach integrating LLM-generated and real data.
result Statistically robust estimators with reduced bias and cost savings.
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.
problem How to allocate costly human effort to correct noisy or biased AI-generated assessments.
method Decision-theoretic framework treating AI assessments as signals and human judgments as costly information. Developed estimation procedures under nonparametric and linear models.
result Our approach substantially outperforms LLM-only predictions and achieves performance comparable to full human review while using only 20-30% of the human information.
Improved NTL detection using human-in-the-loop approach with explainability.
problem Challenges in detecting NTL due to biased data and black-box models.
method Human-in-the-loop approach with explanatory methods to guide model training.
result Improved accuracy, interpretability, robustness, and flexibility of the prediction model.
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…
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…
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…
AI bias arises from human-defined goals, not algorithmic flaws.
problem AI bias due to human-defined goals in LLMs.
method Purpose-conditioned cognition and revealing downstream use of LLM outputs.
result AI bias can be reduced by purpose-aware prompting but not fully by regularization.
Fair Adversarial Networks remove bias from data.
problem Bias in datasets leads to biased outcomes, making analysis illegal and sub-optimal.
method Remove bias from data by altering all proxy variables, ensuring fairness without changing analytical pipelines.
result Fair Adversarial Networks effectively remove bias from data.
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…
Endowing robots with human-like physical reasoning abilities remains challenging. We argue that existing methods often disregard spatio-temporal relations and by using Graph Neural Networks (GNNs) that incorporate a relational inductive bias, we can shift the learning process towards exploiting relations. In this work,…
A simple method reduces bias in LLM auto-evaluators by controlling output length.
problem Bias in LLM auto-annotators, particularly length bias.
method Simple regression analysis to control for length difference and other mediators.
result Improved robustness and increased correlation with human preferences.