paper-with-me

홈 › Papers

Comparing Template-based and Template-free Language Model Probing

2024-01-31 · Sagi Shaier, Kevin Bennett, Lawrence E Hunter, Katharina von der Wense

The differences between cloze-task language model (LM) probing with 1) expert-made templates and 2) naturally-occurring text have often been overlooked. Here, we evaluate 16 different LMs on 10 probing English datasets -- 4 template-based and 6 template-free -- in general and biomedical domains to answer the following research questions: (RQ1) Do model rankings differ between the two approaches? (RQ2) Do models' absolute scores differ between the two approaches? (RQ3) Do the answers to RQ1 and RQ2 differ between general and domain-specific models? Our findings are: 1) Template-free and template-based approaches often rank models differently, except for the top domain-specific models. 2) Scores decrease by up to 42% Acc@1 when comparing parallel template-free and template-based prompts. 3) Perplexity is negatively correlated with accuracy in the template-free approach, but, counter-intuitively, they are positively correlated for template-based probing. 4) Models tend to predict the same answers frequently across prompts for template-based probing, which is less common when employing template-free techniques.

📄 PDF Abstract BibTeX arXiv:2402.00123

Code (1)

shaier/probing_template_based_template_free 공식 구현

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

MALAMUTE: A Multilingual, Highly-granular, Template-free, Education-based Probing Dataset

2024-12-13 · Sagi Shaier, George Arthur Baker, Chiranthan Sridhar, Lawrence E Hunter 외

Language models (LMs) have excelled in various broad domains. However, to ensure their safe and effective integration into real-world educational settings, they must demonstrate proficiency in specific, granular areas of…

Comparing Natural and Synthetic Structured Data: A Study of the Passive Verb Alternation in French and Italian

2026-03-26 · Giuseppe Samo, Paola Merlo arxiv

This study compares the impact of natural and synthetic data on training and evaluating large language models (LLMs), using the case of passive verb alternation in French and Italian. We use Blackbird Language Matrices (…

Counterfactually Probing Language Identity in Multilingual Models

2023-10-29 · Anirudh Srinivasan, Venkata S Govindarajan, Kyle Mahowald

Techniques in causal analysis of language models illuminate how linguistic information is organized in LLMs. We use one such technique, AlterRep, a method of counterfactual probing, to explore the internal structure of m…

counterfactualLanguage ModelingLanguage ModellingMasked Language Modeling+1

Assessing the Extrapolation Capability of Template-Free Retrosynthesis Models

2024-02-29 · Shuan Chen, Yousung Jung

Despite the acknowledged capability of template-free models in exploring unseen reaction spaces compared to template-based models for retrosynthesis prediction, their ability to venture beyond established boundaries rema…

Retrosynthesis

SemiRetro: Semi-template framework boosts deep retrosynthesis prediction

2022-02-12 · Zhangyang Gao, Cheng Tan, Lirong Wu, Stan Z. Li

Recently, template-based (TB) and template-free (TF) molecule graph learning methods have shown promising results to retrosynthesis. TB methods are more accurate using pre-encoded reaction templates, and TF methods are m…

Graph LearningPredictionRetrosynthesis