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

Showing 110 of 458 papers

TitleStatusHype
Invocable APIs derived from NL2SQL datasets for LLM Tool-Calling Evaluation0
Interpretable and Robust Dialogue State Tracking via Natural Language Summarization with LLMs0
A physics-informed Bayesian optimization method for rapid development of electrical machines0
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 Generation0
HiTZ at VarDial 2025 NorSID: Overcoming Data Scarcity with Language Transfer and Automatic Data Annotation0
Advancing Single and Multi-task Text Classification through Large Language Model Fine-tuning0
Zero-shot Slot Filling in the Age of LLMs for Dialogue Systems0
HierTOD: A Task-Oriented Dialogue System Driven by Hierarchical Goals0
Show:102550
← PrevPage 1 of 46Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CTRANF198.3Unverified
2JointBERT-CAEF197Unverified
3Stack-Propagation (+BERT)F197Unverified
4AGIFF194.8Unverified
5Stack-PropagationF194.2Unverified
6Context EncoderF193.6Unverified
7SF-IDF192.23Unverified
8Slot-Gated BLSTM with AttensionF188.8Unverified
9DecomposedMetaSLF1 (1-shot) avg74.89Unverified
10Capsule-NLUF10.92Unverified