mlsanityData to 7 Oct 2026

Meta Semantics: Towards better natural language understanding and reasoning

arXiv 2304.10663 ↗First posted 20 Apr 2023cs.CL cs.AIcited by 0

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Natural language understanding is one of the most challenging topics in artificial intelligence. Deep neural network methods, particularly large language module (LLM) methods such as ChatGPT and GPT-3, have powerful flexibility to adopt informal text but are weak on logical deduction and suffer from the out-of-vocabulary (OOV) problem. On the other hand, rule-based methods such as Mathematica, Semantic web, and Lean, are excellent in reasoning but cannot handle the complex and changeable informal text. Inspired by pragmatics and structuralism, we propose two strategies to solve the OOV problem and a semantic model for better natural language understanding and reasoning.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 7 of its 23 references that are in the map. First posted on arXiv 20 Apr 2023.

Builds on

7 of 23 references.

References · 7

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2023Mathematical Capabilities of ChatGPTcited by 263
  5. 2014word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding methodcited by 109
  6. 2018Translating a Math Word Problem to an Expression Treecited by 57
  7. 2016Learning Executable Semantic Parsers for Natural Language Understandingcited by 21

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language Models
  2. 2026Semantic Abstraction for Natural Language Inference: a Methodological Framework for Discovering and Compensating Semantic Knowledge and Reasoning Gaps in Large Language Models
  3. 2023Large Language Models Are Not Strong Abstract Reasoners
  4. 2025Semantic Mastery: Enhancing LLMs with Advanced Natural Language Understanding
  5. 2023Reliable Natural Language Understanding with Large Language Models and Answer Set Programming
  6. 2023Natural Language Reasoning, A Survey
  7. 2024Large Language Models are Limited in Out-of-Context Knowledge Reasoning
  8. 2024LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models