Skip to main content
Search

University of Chicago

23 related articles

Subscribe to updates
  1. arXiv

    Legal judgment models keep guilty verdicts after the decisive fact changes: PROSE cuts damage to supported rulings from 17.5% to 8.5%

    Legal judgment prediction models often keep a guilty verdict after a legally decisive condition has been altered, a tendency the authors call guilty bias. PROSE frames the correction as a paired constraint: the unsupported member of a case pair should flip, while its counterpart, differing in one decisive condition, should stay. On Qwen3-8B and GLM-4-9B it performs this selective repair through a one-time offline parameter edit, and at matched repair rates it reduces damage to supported verdicts from 17.5% to 8.5% on Qwen and from 24.3% to 7.1% on GLM.

  2. arXiv

    Babylonian Astronomical Diaries no longer dated tablet by tablet: a language model reads the broken text and astronomical tools rank 701 candidate years

    The Babylonian Astronomical Diaries record the sky for nearly six centuries, and many broken tablets have lost their date formula, which specialists previously dated one tablet at a time by comparing the surviving observations with computed phenomena. The new system turns observations into fixed-field clauses with a rule-based parser, has a language model check them against the text and add missed ones, and tests the clauses in all 701 years from 626 BCE to AD 75. On 120 dated tablets with decisive clauses, the top-ranked group contains the published year in 96% of cases; for 86 of them the group is a single year, the published year in 84.

  3. arXiv

    Unit-test rewards teach models to edit more: PreciseCoder cuts average edits from 7–15 lines to 3 without losing pass rate

    Reinforcement learning from unit tests raises pass rates but also teaches code models to edit more and to invent bugs in programs that are already correct. PreciseCoder adds a signal for semantically verified edit precision and recall against a reference repair; on 4B, 9B and 27B models it cuts the average edit from 7–15 lines to 3 at a pass rate on par with unit-test-only training, and raises the no-edit rate on correct code to 47–52%.

  4. bioRxiv

    Individual differences need not each get a model: a six-dimensional shared structure in 155 click-task participants replicates in 102 more

    Differences between individuals in perceptual decision-making may be different mixtures of a few shared computational components. A low-rank neural network learned shared components and participant-specific weights jointly from trial-level choices; on the Bernoulli Clicks Task, out-of-sample prediction selected a six-dimensional representation of individual differences in the first dataset of 155 participants: two dimensions of temporal evidence weighting, two of choice-outcome history dependence, plus participant-specific side bias and signal-to-noise ratio. This low-dimensional organization reappeared in an independent replication dataset of 102 participants.

  5. arXiv

    Humanoid robots learn how hard to press: FLoRe captures contact force from robot-free demos and reaches 80% success on three contact-rich tasks

    Everyday humanoid work such as pushing a cart, moving a box or wiping a surface needs controlled contact force, not just tracked hand motion. FLoRe makes force a shared interface across demonstration, policy and whole-body control: two handheld grippers with six-axis force/torque sensors record hand motion and contact wrenches without a robot, a diffusion policy predicts per-hand force commands from those demonstrations, and a whole-body controller tracks them by integrating the measured force error. On a Unitree G1 across three contact-rich tasks, the force-reactive policy succeeded in 80% of rollouts, against 26.7% for a position-only policy trained on the same demonstrations and run by the same controller.

  6. medRxiv

    Ovarian mass triage without a fixed biomarker panel: adaptive plasma proteomics reaches a summary AUC of 0.835 across five validation cohorts

    Pre-operative triage of adnexal masses has relied on CA-125, HE4 and ultrasound O-RADS, all with limited sensitivity and specificity. ADAPT-MS instead retrains a classifier for each sample on the proteins actually measured, reading discovery-mode plasma mass spectrometry data directly. Across 623 samples in five independent validation cohorts the classifier reached a summary AUC of 0.835, comparable to O-RADS alone, and rose to 0.922 when combined with O-RADS.

  7. arXiv

    Collaboration can backfire when modalities vanish: Lluna keeps a direct per-model prediction and gains 4.26% on average across eight datasets

    Collaboration among pretrained unimodal models can become less accurate than a surviving unimodal model when modalities are missing. Lluna keeps each model's direct prediction as a private path, adds a graph-based common branch as a residual correction, and lets richer availability states guide poorer ones along single-modality removal chains. Across eight datasets in affective computing, scene understanding and medical prediction, it improves Mean-Missing performance by 4.26% on average over the strongest evaluated baseline, with positive collaboration gains at minimal inputs on all eight tasks.

  8. arXiv

    Better task completion, more leakage: 936 executable agent tasks show 32.5% to 94.4% privacy leakage

    AgentCIScope turns privacy cases into 936 executable agent tasks across 11 application environments and finds single-run leakage rates from 32.5% to 94.4% across 12 agents, so strong task completion does not imply contextual integrity.

  9. arXiv

    Rewrite the same commit, and frontier agents lose the bug: transformations mined from real development cut vulnerability-discovery success from 63.3% to 36.8%

    Functionality-preserving code transformations mined from real-world commits cut frontier vulnerability-analysis agents' mean success on CyberGym tasks from 63.3% to 36.8%, while comparable synthetic obfuscations only bring it to 49.7%.

  10. arXiv

    Creativity benchmarks are really testing the tail: scoring only a benchmark's rarest items tracks human preference better

    Sorting creativity benchmarks by how rare their items are under a reference corpus makes the tail subset's model ranking agree more closely with LM Arena creative-writing human preferences than the peak subset, so creativity evaluation can be read as task performance in the long tail.