ELS framework improves safety alignment by dynamically steering LLMs towards helpful responses.
problem Over-Refusal in Aligned Large Language Models
method Fine-tuning free framework using an Energy-Based Model (EBM) to dynamically steer LLMs during inference.
result Extensive experiments show a significant reduction in false refusals (from 57.3% to 82.6%) while maintaining safety performance.
New benchmark uncovers hidden biases in LLMs that refuse to answer certain queries.
problem Evaluating fairness in LLMs, especially in sensitive applications.
method Silenced Bias Benchmark (SBB) using activation steering to reduce model refusals during QA.
result Exposes hidden unfair preferences in LLMs' latent space, distinguishing direct responses from underlying fairness issues.
Localized Multidirectional Correction improves non-refusal target-response behavior in foundation models.
problem Controlled post-training refusal suppression in routed MoE and hybrid-MoE foundation models.
method Introduce Localized Multidirectional Correction (LoMC), a support-gated intervention framework.
result Substantially improves non-refusal target-response behavior while maintaining general capability under a compact intervention footprint.
Deleting refusal directions from models leads to systematically more optimistic decisions.
problem The impact of removing refusal directions from models on decision-making outcomes.
method Ablation study using a frozen pipeline of 21,600 weekly equity decisions.
result Ablation of refusal directions makes models more optimistic and justifies themselves more, but also reduces confidence.
Paper explores MM strategies that can refuse to quote or provide single-sided quotes.
problem Overcoming risks in market making due to changing market conditions.
method Adversarial reinforcement learning with new MM agent designs.
result Refusal to quote or providing single-sided quotes can improve MM performance.
LLM safety alignment explained as divergence estimation.
problem Aligning large language models to avoid harmful outputs.
method Presented a theoretical framework showing alignment methods as divergence estimators.
result KLDO method improves safety alignment using compliance-refusal datasets.
Training models to prefer certain responses can unintentionally shift probability to harmful ones.
problem Likelihood displacement in DPO models, leading to unintended unalignment.
method Characterized and mitigated likelihood displacement using CHES score.
result Training models to prefer certain responses can unintentionally shift probability mass to harmful responses.
A new constructivist approach to modeling in economics and theory of consciousness is proposed. The state of elementary object is defined as a set of its measurable consumer properties. A proprietor's refusal or consent for the offered transaction is considered as a result of elementary economic measurement. We were al…
Machine learning algorithms can unintentionally discriminate; tools detect and fix this.
problem Unintentional discrimination in machine learning algorithms.
method Statistical tools to detect and eliminate biases.
result Tools can identify and mitigate algorithmic discrimination.
Weak form of the Efficiency Market Hypothesis (EMH) excludes predictions of future market movements from historical data and makes the technical analysis (TA) out of law. However the technical analysis is widely used by traders and speculators who steadely refuse to consider the market as a "fair game" and survive with…
LLM sandbox and persona dynamics create unethical reality gaps that shift risk to users.
problem Ethical issues arise from LLMs generating reality gaps that shift risk to uninformed users.
method Analyzes the ethical implications of LLM sandbox and persona dynamics, comparing them to financial regulation and compliance.
result Active generation of reality gaps is unethical as it shifts epistemic risk to users.
In this paper we present detailed simulation results on the wealth distribution model with quenched saving propensities. Unlike other wealth distribution models where the saving propensities are either zero or constant, this model is not found to be ergodic and self-averaging. The wealth distribution statistics with a …
New method controls false discoveries in financial asset pricing.
problem Controlling false discoveries in time series with unknown correlations.
method Double bootstrapping method to control false discovery rate.
result Superior statistical power and controlled false discovery rate.
Model shows bailout stigma affects firm funding and market performance.
problem Bailout stigma impacts firm funding and market stability.
method Developed a model to analyze the effects of bailout stigma on firms and markets.
result Firms avoid stigma by withdrawing or refusing bailouts, leading to market freeze or revival.
New methods control false discoveries near the boundary in conformal novelty detection.
problem Over-optimistic assessments near the rejection threshold in conformal novelty detection.
method Support line (SL) correction and alternative procedures to control boundary false discovery rate (bFDR).
result New procedures control the boundary false discovery rate (bFDR) in the conformal setting.
New method estimates extreme outcomes in heavy-tailed data, breaking circular dependence.
problem Estimating outcomes for extreme events in heavy-tailed data.
method Proposes an ADRF estimator that includes a structured tail-shape output and a diagnostic to evaluate tail shape.
result Successfully reduces MAE in deep-tail and conditional-shortfall predictions.
There are two big unsolved mathematical questions in artificial intelligence (AI): (1) Why is deep learning so successful in classification problems and (2) why are neural nets based on deep learning at the same time universally unstable, where the instabilities make the networks vulnerable to adversarial attacks. We p…
New method controls false edge detections in Gaussian graphical models.
problem High false edge detections in well-established estimators.
method Nodewise variable selection approach to control false discovery rate.
result Significant gain in performance compared to competing methods.
New indefinite false theta functions match homological blocks for a specific 3-manifold.
problem Constructing homological blocks for certain 3-manifolds.
method Developing indefinite false theta functions and proving their equivalence to homological blocks.
result Indefinite false theta functions match homological blocks for the Poincaré homology sphere.
Learning a classifier with control on the false-positive rate plays a critical role in many machine learning applications. Existing approaches either introduce prior knowledge dependent label cost or tune parameters based on traditional classifiers, which lack consistency in methodology because they do not strictly adh…
Optimizes latency and false alarm probability in change detection problems.
problem Balancing latency and false alarms in non-stationary environments.
method Develops order-optimal change detectors under specified latency and false alarm levels.
result Derives a universal lower bound on latency and develops order-optimal detectors.
A new constructivist approach to modeling in economics and theory of consciousness is proposed. The state of elementary object is defined as a set of its measurable consumer properties. A proprietor's refusal or consent for the offered transaction is considered as a result of elementary economic measurement. Elementary…
New models extrapolate false alarms in ASV without new data.
problem Reliable extrapolation of false alarm rates in ASV without new speaker data.
method Generative models in ASV score space for arbitrary systems.
result Models accurately extrapolate false alarm rates for large speaker populations.
A new metric, Weighted Regret, unifies FDR and power evaluation in online multiple testing.
problem The asymmetric costs of false positives and false negatives in automated pipelines.
method Introducing Weighted Regret and Decoupled-OMT (DOMT) to unify FDR and power evaluation.
result DOMT achieves an order-optimal sublinear mitigation of threshold depletion in bursty environments.
Private online FDR control for adaptive testing under differential privacy.
problem Controlling false discoveries in adaptive multiple hypothesis testing with privacy constraints.
method Private online algorithms based on non-private results, ensuring privacy and statistical performance.
result Strong guarantees for privacy and statistical performance in FDR and power.
New method calibrates false detection rates in sequential change detection.
problem Challenges in setting time-invariant thresholds for false positives.
method Simulation-based approach to time-varying thresholds.
result Accurately targets desired expected runtime while keeping false positive rate constant.
Nonparametric IPSS selects features with false discovery control.
problem Feature selection in high-dimensional data with theoretical false discovery control.
method Integrated Path Stability Selection (IPSS) applied to nonparametric feature importance scores.
result IPSS accurately controls false discovery rate and detects more true positives than existing methods.
Accurate on-device keyword spotting (KWS) with low false accept and false reject rate is crucial to customer experience for far-field voice control of conversational agents. It is particularly challenging to maintain low false reject rate in real world conditions where there is (a) ambient noise from external sources s…
Paper tackles MIAs vulnerability by controlling FDR, providing guarantees on false discoveries.
problem Vulnerability of deep learning models to membership inference attacks (MIAs).
method Designs a novel membership inference attack method that provides FDR guarantees.
result Demonstrates the effectiveness of the method in various settings.
Knockoffs method selects financial factors, controlling false discoveries.
problem Controlling false discoveries in financial factor selection.
method Apply knockoff procedure to build fake factors.
result Shows versatility in fund replication and network inference.
Paper proposes knockoff-based methods to simplify deep neural networks by controlling false discovery rates.
problem High-dimensional deep neural networks with many irrelevant parameters and inputs.
method Knockoff methods combined with regularized neural networks for variable screening.
result Proposed algorithms show satisfactory performance in controlling false discovery rates.
Nowadays, advanced intrusion detection systems (IDSs) rely on a combination of anomaly detection and signature-based methods. An IDS gathers observations, analyzes behavioral patterns, and reports suspicious events for further investigation. A notorious issue anomaly detection systems (ADSs) and IDSs face is the possib…
Study controls error rates of binary classifiers using hypothesis testing.
problem Traditional binary classifiers have uncontrolled error rates.
method Combines binary classification with statistical hypothesis testing.
result Trained classifiers can be made to meet target error rate thresholds.
Donoho's JCGS (in press) paper is a spirited call to action for statisticians, who he points out are losing ground in the field of data science by refusing to accept that data science is its own domain. (Or, at least, a domain that is becoming distinctly defined.) He calls on writings by John Tukey, Bill Cleveland, and…
New method controls false discoveries in online testing with deadlines.
problem Controlling false discoveries in online hypothesis testing with decision deadlines.
method Benjamini-Hochberg-type procedure over a moving window of hypotheses with adaptive threshold parameters.
result Controls false discovery rate at every stage and adaptively chosen stopping times.
Efron et al. (2001) proposed empirical Bayes formulation of the frequentist Benjamini and Hochbergs False Discovery Rate method (Benjamini and Hochberg,1995). This article attempts to unify the `two cultures' using concepts of comparison density and distribution function. We have also shown how almost all of the existi…
Proposes a method to handle sparse multiway count data with false zeros using zero-truncated Poisson regression.
problem Handling sparse multiway count data corrupted by false zeros.
method Zero-truncated Poisson regression with tensor completion.
result Accurate estimation of multiway count data from approximately IR2log22(I) non-zero counts. Develops robust knockoffs for controlling false discoveries in financial data.
problem Challenges in variable selection with highly correlated data in finance and economics.
method Robustified knockoff framework addressing high dependence and time correlation.
result Identifies new important groups of factors on top of known drivers.
New algorithm for adaptive experimental design in scientific settings.
problem Identifying true positives while controlling false discoveries in adaptive experimental design.
method Provably sample efficient adaptive algorithm for FDR control.
result First provably sample efficient adaptive algorithm for adaptive experimental design.
Paper is withdrawn due to errors (superseded by math.AG/0604303). Formula 6.5 is false. Section 6 is false, and the main statement is true only for bundles B with c1(B) SU(2)-invariant.
Paper withdrawn due to errors (superseded by math.AG/0604303). Proposition 11.4 is false, Section 12 is false, and the main statement is true only for bundles B with c1(B) SU(2)-invariant.
This paper addresses the problem of inferring sparse causal networks modeled by multivariate auto-regressive (MAR) processes. Conditions are derived under which the Group Lasso (gLasso) procedure consistently estimates sparse network structure. The key condition involves a "false connection score." In particular, we sh…
Valid certifies LLMs' domain adherence, bounding out-of-domain behavior.
problem Adversarial susceptibility of LLMs to generate out-of-domain outputs.
method VALID approach providing adversarial bounds as a certificate.
result Validates LLMs' domain adherence with meaningful certificates.
Online anomaly detection in surveillance videos with false alarm rate bounds.
problem Lack of theoretical performance analysis and online decision making in anomaly detection.
method Proposes an online anomaly detection method with asymptotic bounds on false alarm rate.
result Demonstrates effectiveness on publicly available data sets, outperforming state-of-the-art algorithms.
Detects data drift in deep learning models using neural embeddings.
problem Detecting changes in data distribution in deep learning models.
method Formulates drift detection in a sequential decision framework and introduces a loss function to balance false alarms and quick detection.
result Demonstrates improved ability to balance false alarms and quick detection in change detection.
In recent years, deep learning methods have outperformed other methods in image recognition. This has fostered imagination of potential application of deep learning technology including safety relevant applications like the interpretation of medical images or autonomous driving. The passage from assistance of a human d…
Multiple hypothesis testing is a core problem in statistical inference and arises in almost every scientific field. Given a set of null hypotheses H(n)=(H1,…,Hn), Benjamini and Hochberg introduced the false discovery rate (FDR), which is the expected proportion of false positives among rejected nu…
The paper controls false discovery rate in link prediction using conformal inference.
problem Identifying true edges in a graph while controlling false discoveries.
method Proposes a novel method based on conformal inference to control false discovery rate (FDR) in link prediction.
result Empirically demonstrates FDR control for both simulated and real data.