Papers with semantic correctness
Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue (P19-1)
Copied to clipboard
| Challenge: | Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems. |
| Approach: | They propose using tree-structured semantic representations for better discourse-level structuring and sentence-level planning and introduce a challenging dataset using this representation for the weather domain. |
| Outcome: | The proposed model improves discourse-level structuring and sentence-level planning on a weather domain and can be decoded to improve semantic correctness. |
SemRegex: A Semantics-Based Approach for Generating Regular Expressions from Natural Language Specifications (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to generate programs from natural language do not address program aliasing . semantically equivalent programs may have many syntactically different forms . |
| Approach: | They propose a semantics-based approach to generate regular expressions from natural language. |
| Outcome: | The proposed approach improves on three public datasets. |
NL2Logic: AST-Guided Translation of Natural Language into First-Order Logic with Large Language Models (2026.findings-eacl)
Copied to clipboard
| Challenge: | Structured reasoning approaches that parse first-order logic rules from natural language lack syntax control and semantic faithfulness. |
| Approach: | They propose a structured reasoning paradigm that parses first-order logic rules from natural language and delegates inference to automated solvers. |
| Outcome: | a proposed framework parses first-order logic rules from natural language and delegates inference to automated solvers. |
ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for code execution reasoning are limited by the difficulty of the training data. |
| Approach: | They propose a model that uses reinforcement learning to reward correct answers from execution traces. |
| Outcome: | The proposed model improves pass@1 by up to 5.9% on code generation tasks over strong baselines. |