Domainless Adaptation by Constrained Decoding on a Schema Lattice
In many applications such as personal digital assistants, there is a constant need for new domains to increase the system{'}s coverage of user queries. A conventional approach is to learn a separate model every time a new domain is introduced. This approach is slow, inefficient, and a bottleneck for scaling to a large number of domains. In this paper, we introduce a framework that allows us to have a single model that can handle all domains: including unknown domains that may be created in the future as long as they are covered in the master schema. The key idea is to remove the need for distinguishing domains by explicitly predicting the schema of queries. Given permitted schema of a query, we perform constrained decoding on a lattice of slot sequences allowed under the schema. The proposed model achieves competitive and often superior performance over the conventional model trained separately per domain.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-Label ClassificationSpoken Language UnderstandingSimilar Papers 제목 키워드 기반
XML Prompting as Grammar-Constrained Interaction: Fixed-Point Semantics, Convergence Guarantees, and Human-AI Protocols
Structured prompting with XML tags has emerged as an effective way to steer large language models (LLMs) toward parseable, schema-adherent outputs in real-world systems. We develop a logic-first treatment of XML promptin…
Generating Structured Outputs from Language Models: Benchmark and Studies
Reliably generating structured outputs has become a critical capability for modern language model (LM) applications. Constrained decoding has emerged as the dominant technology across sectors for enforcing structured out…
Schema Key Wording as an Instruction Channel in Structured Generation under Constrained Decoding
Constrained decoding is widely used to make large language models produce structured outputs that satisfy schemas such as JSON. Existing work mainly treats schemas as structural constraints, overlooking that schema-key t…
Mathematical ReasoningTo Know is to Construct: Schema-Constrained Generation for Agent Memory
Constructivist epistemology argues that knowledge is actively constructed rather than passively copied. Despite the generative nature of Large Language Models (LLMs), most existing agent memory systems are still based on…
Small Language Models for Agentic Systems: A Survey of Architectures, Capabilities, and Deployment Trade offs
Small language models (SLMs; 1-12B params, sometimes up to 20B) are sufficient and often superior for agentic workloads where the objective is schema- and API-constrained accuracy rather than open-ended generation. We sy…