REVIEW 10 cited by
PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models
read the original abstract
Large pre-trained language models for textual data have an unconstrained output space; at each decoding step, they can produce any of 10,000s of sub-word tokens. When fine-tuned to target constrained formal languages like SQL, these models often generate invalid code, rendering it unusable. We propose PICARD (code and trained models available at https://github.com/ElementAI/picard), a method for constraining auto-regressive decoders of language models through incremental parsing. PICARD helps to find valid output sequences by rejecting inadmissible tokens at each decoding step. On the challenging Spider and CoSQL text-to-SQL translation tasks, we show that PICARD transforms fine-tuned T5 models with passable performance into state-of-the-art solutions.
Forward citations
Cited by 10 Pith papers
-
EcoTable: Cost-effective Table Integration in Data Lakes for Natural Language Queries
EcoTable is the first NL-based data integration framework that builds a join-likelihood graph, uses two-stage schema linking and Steiner tree search to find paths, then generates transformations with LLMs, reporting >...
-
EcoTable: Cost-effective Table Integration in Data Lakes for Natural Language Queries
Query-driven table integration that uses Steiner-tree search to choose which joins LLMs must verify, reporting 30%+ accuracy gains at 5x lower LLM cost.
-
To Know is to Construct: Schema-Constrained Generation for Agent Memory
SCG-MEM reformulates agent memory access as schema-constrained generation within dynamic cognitive schemas, using assimilation and accommodation for updates plus an associative graph for reasoning, and outperforms ret...
-
Natural Language Interfaces for Spatial and Temporal Databases: A Comprehensive Overview of Methods, Taxonomy, and Future Directions
A literature survey that taxonomizes methods, datasets, and evaluation practices for natural language interfaces to geospatial and temporal databases while identifying recurring trends and future directions.
-
XGrammar-2: Efficient Dynamic Structured Generation Engine for Agentic LLMs
XGrammar-2 makes dynamic, tag-triggered structured generation fast by dispatching to cached substructure grammars with an Earley-based adaptive token-mask cache.
-
TreeCoder: Systematic Exploration and Optimisation of Decoding and Constraints for LLM Code Generation
TreeCoder improves LLM code generation accuracy by representing decoding as an optimizable tree search over programs with first-class constraints for syntax, style, and execution, outperforming baselines on MBPP and S...
-
Theory-Level Autoformalization: From Isolated Statements to Unified Formal Knowledge Bases
Autoformalization should target complete theories—axioms, definitions, lemmas, proofs—as unified formal libraries, not isolated statements.
-
CogRAG: Tackling Heterogeneous Cognitive Demands in RAG via Stratified Retrieval and Reasoning
Stratifying RAG retrieval and reasoning by predicted cognitive load (Bloom-inspired) raises Qwen3-8B accuracy on a dietitian exam from 73.4% to 85.8% (single-choice) and 63.3% to 80.5% (scenario).
-
TAHOE: Text-to-SQL with Automated Hint Optimization from Experience
TAHOE builds a Hint Bank from error traces to raise Text-to-SQL pass rates on Spider 2.0-Snow from 61.95% to 79.42% for GPT-5.5 without parameter updates.
-
CogRAG: Tackling Heterogeneous Cognitive Demands in RAG via Stratified Retrieval and Reasoning
CogRAG+ raises LLM accuracy on a dietitian exam to 85.8% by using dual-path retrieval and structured reasoning templates.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.