LLMs Fail Cultural Recipes
LLMs generate culturally unrepresentative recipe adaptations unlike humans. Outputs ignore cultural distance correlations from GlobalFusion dataset. Issues stem from weak cultural representations and novelty inflation.
Search
Tag: #v1120 results
LLMs Accelerate Systematic Mapping
Experience report on using LLMs for systematic mapping studies. Highlights time savings in screening and extraction but notes challenges like hallucinations and prompt engineering. Offers lessons and recommendations for adoption.
LLM Evolutionary Sampling Speeds Databases
DBPlanBench exposes physical query plans for LLM-proposed localized edits, refined via evolutionary search. LLMs leverage semantic knowledge for optimizations like join orderings. Achieves up to 4.78x speedups, with transfers from small to large databases.
LLM Agents Auto-Optimize RecSys Models
A self-evolving system uses Google's Gemini LLMs to autonomously generate, train, and deploy recommendation model improvements. It features an Offline Agent for hypothesis generation and an Online Agent for production validation. Deployed successfully at YouTube, surpassing manual workflows.
LITT: Timing Transformer for EHR Events
LITT introduces a Timing-Transformer architecture that aligns sequential events on a virtual relative timeline for event-timing-focused attention. It enables personalized clinical trajectory interpretations. Validated on EHR data from 3,276 breast cancer patients to predict cardiotoxicity onset.
Latent Flows Model Reaction Trajectories
LatentRxnFlow predicts reactions as continuous latent trajectories via Conditional Flow Matching from reactant-product pairs. Offers SOTA USPTO accuracy with trajectory diagnostics and uncertainty estimation. Enables error mitigation and reliable predictions.
LAP Achieves Zero-Shot Robot Embodiment Transfer
Language-Action Pre-training (LAP) represents robot actions in natural language for zero-shot transfer across embodiments without fine-tuning. LAP-3B, a 3B VLA, delivers over 50% success on novel robots and tasks. Enables efficient adaptation and unifies action prediction with VQA.
KSTER Attacks Reverse LLM Model Edits
KSTER exploits low-rank updates in locate-then-edit methods to recover edited data via spectral keyspace reconstruction and entropy prompt recovery. Achieves high success on multiple LLMs. Defense subspace camouflage uses decoys to hide fingerprints.
KPO Stabilizes LLM Policy Optimization
Online Causal Kalman Filtering models IS ratios as evolving latent states for stable RL in LLMs. Smooths noise while preserving token structure. Superior on math reasoning datasets.
KG-Guided LLM for SSD Analysis
KORAL integrates LLMs with Data and Literature Knowledge Graphs for SSD diagnostics from fragmented telemetry. Provides descriptive, predictive, prescriptive, what-if analysis with explainable insights. Outperforms expert methods on production traces.