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.

168,657 papers · 148 categories

Trend · papers per month

count% of corpus
1122 · Aug 202519922001200920172026
3 results for “Confabulations”
Topic Identification in LLM Input-Output Pairs through the Lens of Information Bottleneckcs.CL

New method identifies shared topics in LLM inputs and outputs for better detection of hallucinations.

problem Detecting semantic drift in LLM responses from context.
method Transformed Deterministic Information Bottleneck (DIB) into UDIB for high-dimensional data.
result UDIB generates more informative topic representations for SDM, improving hallucination detection.
Large Language ModelsSemantic Divergence MetricsInformation BottleneckK-meansEntropy-regularized
2025-08-26abs ↗pdf ↗
Prompt-Response Semantic Divergence Metrics for Faithfulness Hallucination and Misalignment Detection in Large Language Modelscs.CL

Paper introduces SDM for detecting LLM hallucinations, improving on entropy tests.

problem Challenges of Large Language Models (LLMs) with non-factual, nonsensical responses.
method Joint clustering on sentence embeddings to measure semantic divergence between prompts and responses.
result SDM framework detects deeper form of arbitrariness in LLM responses.
Large Language ModelsSemantic Divergence MetricsHallucinationsConfabulationsSemantic Entropy
2025-08-13abs ↗pdf ↗