Research
On-device research index

arXiv research

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.

168,695 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · Apr 202419922001200920172026
2 results for “logprobs”
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attackscs.CR

Simple adaptive attacks can jailbreak state-of-the-art safety-aligned language models.

problem Vulnerability of safety-aligned language models to simple adaptive attacks.
method Designing adversarial prompt templates, random search on suffixes, and transfer/prefilling attacks.
result 100% attack success rate on various models including GPT-4, Vicuna, Mistral, and Claude.
language modelsadaptive attacksjailbreakingsafetylogprobs
2024-04-02abs ↗pdf ↗
Detecting AI Hallucinations in Finance: An Information-Theoretic Method Cuts Hallucination Rate by 92%cs.LG

ECLIPSE detects AI hallucinations in finance with high accuracy.

problem Hallucinations in AI-generated answers limit safe deployment in finance.
method Combines entropy estimation and perplexity decomposition to measure model evidence use.
result ECLIPSE achieves ROC AUC of 0.89 and average precision of 0.90 on financial QA dataset.
AI hallucinationsfinancial QAentropy estimationperplexity decompositionlog probabilities
2025-12-02abs ↗pdf ↗