SOTAVerified

Slot Filling

The goal of Slot Filling is to identify from a running dialog different slots, which correspond to different parameters of the user’s query. For instance, when a user queries for nearby restaurants, key slots for location and preferred food are required for a dialog system to retrieve the appropriate information. Thus, the main challenge in the slot-filling task is to extract the target entity.

Source: Real-time On-Demand Crowd-powered Entity Extraction

Image credit: Robust Retrieval Augmented Generation for Zero-shot Slot Filling

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 458 papers

TitleStatusHype
Invocable APIs derived from NL2SQL datasets for LLM Tool-Calling Evaluation—0
Interpretable and Robust Dialogue State Tracking via Natural Language Summarization with LLMs—0
A physics-informed Bayesian optimization method for rapid development of electrical machines—0
Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMsCode1
Improving Dialectal Slot and Intent Detection with Auxiliary Tasks: A Multi-Dialectal Bavarian Case StudyCode0
A Career Interview Dialogue System using Large Language Model-based Dynamic Slot Generation—0
HiTZ at VarDial 2025 NorSID: Overcoming Data Scarcity with Language Transfer and Automatic Data Annotation—0
Advancing Single and Multi-task Text Classification through Large Language Model Fine-tuning—0
Zero-shot Slot Filling in the Age of LLMs for Dialogue Systems—0
HierTOD: A Task-Oriented Dialogue System Driven by Hierarchical Goals—0
Show:102550
← PrevPage 1 of 46Next →
All datasetsKILT: Zero Shot REKILT: T-RExMixSNIPSMixATISATISSNIPSSLURPMASSIVEATIS (vi)CAISDialogue State Tracking ChallengeMULTIWOZ 2.2

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1XLM-R BaseSlot F1 Score83.6—Unverified
2mT5 Base (encoder-only)Slot F1 Score82.2—Unverified
3mT5 Base (text-to-text)Slot F1 Score81.3—Unverified