paper-with-me

Papers

Infusing Prompts with Syntax and Semantics

2024-12-08 · Anton Bulle Labate, Fabio Gagliardi Cozman

Despite impressive success, language models often generate outputs with flawed linguistic structure. We analyze the effect of directly infusing various kinds of syntactic and semantic information into large language models. To demonstrate the value of our proposals, we focus on the translation of natural language queries to SQL, in particular dealing with languages with less resources than English, to better investigate how much help we can get from low cost syntactic and semantic information. We show that linguistic analysis can significantly boost language models, to the point that we have surpassed previous best systems.

📄 PDF Abstract BibTeX arXiv:2412.06107

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language QueriesTranslation

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Dissecting Paraphrases: The Impact of Prompt Syntax and supplementary Information on Knowledge Retrieval from Pretrained Language Models

2024-04-02 · Stephan Linzbach, Dimitar Dimitrov, Laura Kallmeyer, Kilian Evang 외

Pre-trained Language Models (PLMs) are known to contain various kinds of knowledge. One method to infer relational knowledge is through the use of cloze-style prompts, where a model is tasked to predict missing subjects …

Retrieval

Addressing LLM Diversity by Infusing Random Concepts

2026-01-26 · Pulin Agrawal, Prasoon Goyal arxiv

Large language models (LLMs) are known to produce outputs with limited diversity. In this work, we study whether infusing random concepts in the prompts can improve the diversity of the generated outputs. To benchmark th…

Syntax-Enhanced Pre-trained Model

2020-12-28 · ACL 2021 5 · Zenan Xu, Daya Guo, Duyu Tang, Qinliang Su 외

We study the problem of leveraging the syntactic structure of text to enhance pre-trained models such as BERT and RoBERTa. Existing methods utilize syntax of text either in the pre-training stage or in the fine-tuning st…

Entity TypingmodelQuestion AnsweringRelation Classification

Infusing Finetuning with Semantic Dependencies

2020-12-10 · Zhaofeng Wu, Hao Peng, Noah A. Smith

For natural language processing systems, two kinds of evidence support the use of text representations from neural language models "pretrained" on large unannotated corpora: performance on application-inspired benchmarks…

Natural Language Understanding

Unveiling Code Pre-Trained Models: Investigating Syntax and Semantics Capacities

2022-12-20 · Wei Ma, Shangqing Liu, Mengjie Zhao, Xiaofei Xie 외

Past research has examined how well these models grasp code syntax, yet their understanding of code semantics still needs to be explored. We extensively analyze seven code models to investigate how code models represent …

Code CompletionCode SearchLanguage ModellingProgram Synthesis