The Likelihood Ratio Wall: Structural Limits on Accurate Risk Assessment for Rare Violence

• URL: http://arxiv.org/abs/2604.27282v1
• Date: Thu, 30 Apr 2026 00:32:52 GMT
• Title: The Likelihood Ratio Wall: Structural Limits on Accurate Risk Assessment for Rare Violence
• Abstract summary: Pretrial risk assessment tools are used on over one million U.S. defendants each year.<n>We show that their use for predicting rare violent re-offense faces a basic statistical barrier.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pretrial risk assessment tools are used on over one million U.S. defendants each year, yet their use for predicting rare violent re-offense faces a basic statistical barrier. We derive a universal precision bound -- the Likelihood Ratio Wall -- showing that when violent re-arrest rates are low (2-5%), achieving even a 50% hit rate among people labeled "high risk" (positive predictive value, or PPV) would require tools far more discriminative than current instruments appear to be. For rare outcomes, a tool can have respectable-looking performance metrics and still be wrong most of the time it flags someone as "high risk for violence." We show that post-hoc score recalibration cannot solve this problem because it does not improve the tool's underlying ability to separate true positives from false positives. We further prove a Surveillance Ceiling: when over-policing inflates recorded "risk factors" among those who would not re-offend, the maximum achievable precision is structurally lower for over-policed groups, even at equal offense rates. We translate these results into the Number Needed to Detain (how many people must be detained to prevent one violent offense), and propose that risk reports should communicate this uncertainty explicitly. Our findings suggest that for rare violent outcomes, debates about fairness metrics alone are incomplete: under current data regimes, the available features may not support high-confidence individualized detention decisions.

Related papers

• FinAbstain: Uncertainty-Calibrated Multimodal RAG for Selective Financial Forecasting [8.891247829087936]
  FinAbstain is a framework for uncertainty-calibrated multimodal retrieval-augmented generation with selective prediction.<n>A point-in-time retriever admits only information public at the forecast timestamp and supplies modality-specific evidence to fundamental, news, technical, risk, and verification agents.<n>A controller predicts bullish, bearish, or neutral outcomes only when uncertainty is below a validated threshold.
  arXiv  Detail & Related papers  (2026-07-27T07:05:22Z)
• A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness [57.510025257780306]
  We show that existing validation protocols fail to account for substantial distribution shifts inherent to red-teaming.<n>We propose ReliableBench, a benchmark of behaviors that remain more consistently judgeable, and JudgeStressTest, a dataset designed to expose judge failures.
  arXiv  Detail & Related papers  (2026-02-04T15:13:35Z)
• Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling [50.872910438715486]
  Large Language Models (LLMs) are typically evaluated for safety under single-shot or low-budget adversarial prompting.<n>We propose a scaling-aware Best-of-N estimation of risk, SABER, for modeling jailbreak vulnerability under Best-of-N sampling.
  arXiv  Detail & Related papers  (2026-01-30T06:54:35Z)
• COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees [51.5976496056012]
  COIN is an uncertainty-guarding selection framework that calibrates statistically valid thresholds to filter a single generated answer per question.<n>COIN estimates the empirical error rate on a calibration set and applies confidence interval methods to establish a high-probability upper bound on the true error rate.<n>We demonstrate COIN's robustness in risk control, strong test-time power in retaining admissible answers, and predictive efficiency under limited calibration data.
  arXiv  Detail & Related papers  (2025-06-25T07:04:49Z)
• Criticality and Safety Margins for Reinforcement Learning [53.10194953873209]
  We seek to define a criticality framework with both a quantifiable ground truth and a clear significance to users.<n>We introduce true criticality as the expected drop in reward when an agent deviates from its policy for n consecutive random actions.<n>We also introduce the concept of proxy criticality, a low-overhead metric that has a statistically monotonic relationship to true criticality.
  arXiv  Detail & Related papers  (2024-09-26T21:00:45Z)
• Auditing Fairness under Unobserved Confounding [56.61738581796362]
  We show that, surprisingly, one can still compute meaningful bounds on treatment rates for high-risk individuals.<n>We use the fact that in many real-world settings we have data from prior to any allocation to derive unbiased estimates of risk.
  arXiv  Detail & Related papers  (2024-03-18T21:09:06Z)
• The Progression of Disparities within the Criminal Justice System: Differential Enforcement and Risk Assessment Instruments [26.018802058292614]
  Algorithmic risk assessment instruments (RAIs) increasingly inform decision-making in criminal justice. Problematically, the extent to which arrests reflect overall offending can vary with the person's characteristics. We examine how the disconnect between crime and arrest rates impacts RAIs and their evaluation.
  arXiv  Detail & Related papers  (2023-05-12T16:06:40Z)
• Safe Deployment for Counterfactual Learning to Rank with Exposure-Based Risk Minimization [63.93275508300137]
  We introduce a novel risk-aware Counterfactual Learning To Rank method with theoretical guarantees for safe deployment. Our experimental results demonstrate the efficacy of our proposed method, which is effective at avoiding initial periods of bad performance when little data is available.
  arXiv  Detail & Related papers  (2023-04-26T15:54:23Z)
• Holdouts set for safe predictive model updating [0.4499833362998489]
  We propose using a holdout set' - a subset of the population that does not receive interventions guided by the risk score.<n>We show that, in order to minimise the number of pre-eclampsia cases over time, this is best achieved using a holdout set of around 10,000 individuals.
  arXiv  Detail & Related papers  (2022-02-13T18:04:00Z)
• A Risk Assessment of a Pretrial Risk Assessment Tool: Tussles, Mitigation Strategies, and Inherent Limits [0.0]
  We perform a risk assessment of the Public Safety Assessment (PSA), a software used in San Francisco and other jurisdictions to assist judges in deciding whether defendants need to be detained before their trial. We articulate benefits and limitations of the PSA solution, as well as suggest mitigation strategies. We then draft the Handoff Tree, a novel algorithmic approach to pretrial justice that accommodates some of the inherent limitations of risk assessment tools by design.
  arXiv  Detail & Related papers  (2020-05-14T23:56:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.