{"url":"/method/glm","slug":"glm","name":"GLM","full_name":"GLM","full_name_withheld":false,"description_markdown":"**GLM** is a bilingual (English and Chinese) pre-trained transformer-based language model that follow the traditional architecture of decoder-only autoregressive language modeling. It leverages autoregressive blank infilling as its training objective.","description_state":"present","introduced_year":null,"introduced_by":{"title":"GLM-130B: An Open Bilingual Pre-trained Model","paper":"/paper/glm-130b-an-open-bilingual-pre-trained-model","first_author":"Aohan Zeng","n_authors":18,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/glm-130b-an-open-bilingual-pre-trained-model"},"source":{"url":"https://arxiv.org/abs/2210.02414v2","title":"GLM-130B: An Open Bilingual Pre-trained Model","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Language Models","url":"/methods/category/language-models","pwc_aliases":[]}],"n_papers_tagged":46,"archive_num_papers":46,"papers_newest_first":[{"paper":null,"title":"Identifying interactions across brain areas while accounting for individual-neuron dynamics with a Transformer-based variational autoencoder","date":"2025-06-02","arxiv_id":"2506.02263","n_code_links":0,"syntology":null},{"paper":null,"title":"Confidence Sequences for Generalized Linear Models via Regret Analysis","date":"2025-04-23","arxiv_id":"2504.16555","n_code_links":0,"syntology":null},{"paper":null,"title":"Explainable Boosting Machine for Predicting Claim Severity and Frequency in Car Insurance","date":"2025-03-27","arxiv_id":"2503.21321","n_code_links":0,"syntology":null},{"paper":null,"title":"A Comparative Analysis of Word Segmentation, Part-of-Speech Tagging, and Named Entity Recognition for Historical Chinese Sources, 1900-1950","date":"2025-03-25","arxiv_id":"2503.19844","n_code_links":0,"syntology":null},{"paper":"/paper/scale-free-graph-language-models","title":"Scale-Free Graph-Language Models","date":"2025-02-21","arxiv_id":"2502.15189","n_code_links":1,"syntology":null},{"paper":null,"title":"Robustly Learning Monotone Generalized Linear Models via Data Augmentation","date":"2025-02-12","arxiv_id":"2502.08611","n_code_links":0,"syntology":null},{"paper":null,"title":"Human-Calibrated Automated Testing and Validation of Generative Language Models","date":"2024-11-25","arxiv_id":"2411.16391","n_code_links":0,"syntology":null},{"paper":null,"title":"Gradient dynamics for low-rank fine-tuning beyond kernels","date":"2024-11-23","arxiv_id":"2411.15385","n_code_links":0,"syntology":null},{"paper":null,"title":"Generative Language Models with Retrieval Augmented Generation for Automated Short Answer Scoring","date":"2024-08-07","arxiv_id":"2408.03811","n_code_links":0,"syntology":null},{"paper":null,"title":"Particle swarm optimization with Applications to Maximum Likelihood Estimation and Penalized Negative Binomial Regression","date":"2024-05-20","arxiv_id":"2405.12386","n_code_links":0,"syntology":null},{"paper":null,"title":"Impact of Preference Noise on the Alignment Performance of Generative Language Models","date":"2024-04-15","arxiv_id":"2404.09824","n_code_links":0,"syntology":null},{"paper":null,"title":"Hedonic Models Incorporating ESG Factors for Time Series of Average Annual Home Prices","date":"2024-04-10","arxiv_id":"2404.07132","n_code_links":0,"syntology":null},{"paper":"/paper/length-controlled-alpacaeval-a-simple-way-to","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","date":"2024-04-06","arxiv_id":"2404.04475","n_code_links":2,"syntology":null},{"paper":"/paper/graph-language-models","title":"Graph Language Models","date":"2024-01-13","arxiv_id":"2401.07105","n_code_links":1,"syntology":{"ran":7,"of":9,"unverified":2,"pointer_only":9}},{"paper":"/paper/nlebench-norglm-a-comprehensive-empirical","title":"NLEBench+NorGLM: A Comprehensive Empirical Analysis and Benchmark Dataset for Generative Language Models in Norwegian","date":"2023-12-03","arxiv_id":"2312.01314","n_code_links":1,"syntology":{"ran":0,"of":4,"unverified":4,"pointer_only":4}},{"paper":"/paper/are-we-falling-in-a-middle-intelligence-trap","title":"An Analysis and Mitigation of the Reversal Curse","date":"2023-11-13","arxiv_id":"2311.07468","n_code_links":1,"syntology":{"ran":4,"of":14,"unverified":10,"pointer_only":14}},{"paper":null,"title":"Causal Discovery with Generalized Linear Models through Peeling Algorithms","date":"2023-10-25","arxiv_id":"2310.16698","n_code_links":0,"syntology":null},{"paper":null,"title":"General Point Model with Autoencoding and Autoregressive","date":"2023-10-25","arxiv_id":"2310.16861","n_code_links":0,"syntology":null},{"paper":null,"title":"One-hot Generalized Linear Model for Switching Brain State Discovery","date":"2023-10-23","arxiv_id":"2310.15263","n_code_links":0,"syntology":null},{"paper":"/paper/neural-networks-for-insurance-pricing-with","title":"Neural networks for insurance pricing with frequency and severity data: a benchmark study from data preprocessing to technical tariff","date":"2023-10-19","arxiv_id":"2310.12671","n_code_links":1,"syntology":null},{"paper":null,"title":"On existence, uniqueness and scalability of adversarial robustness measures for AI classifiers","date":"2023-10-19","arxiv_id":"2310.14421","n_code_links":0,"syntology":null},{"paper":"/paper/fate-llm-a-industrial-grade-federated","title":"FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Models","date":"2023-10-16","arxiv_id":"2310.10049","n_code_links":1,"syntology":{"ran":2,"of":5,"unverified":3,"pointer_only":0}},{"paper":null,"title":"CLIP Is Also a Good Teacher: A New Learning Framework for Inductive Zero-shot Semantic Segmentation","date":"2023-10-03","arxiv_id":"2310.02296","n_code_links":0,"syntology":null},{"paper":null,"title":"Distribution-Independent Regression for Generalized Linear Models with Oblivious Corruptions","date":"2023-09-20","arxiv_id":"2309.11657","n_code_links":0,"syntology":null},{"paper":null,"title":"Structured Low-Rank Tensors for Generalized Linear Models","date":"2023-08-05","arxiv_id":"2308.02922","n_code_links":0,"syntology":null},{"paper":"/paper/mdi-a-flexible-random-forest-based-feature","title":"Integrating Random Forests and Generalized Linear Models for Improved Accuracy and Interpretability","date":"2023-07-04","arxiv_id":"2307.01932","n_code_links":2,"syntology":null},{"paper":null,"title":"Evaluating the Utility of GAN Generated Synthetic Tabular Data for Class Balancing and Low Resource Settings","date":"2023-06-24","arxiv_id":"2306.13929","n_code_links":0,"syntology":null},{"paper":"/paper/webglm-towards-an-efficient-web-enhanced","title":"WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferences","date":"2023-06-13","arxiv_id":"2306.07906","n_code_links":2,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":0}},{"paper":null,"title":"On the Amplification of Linguistic Bias through Unintentional Self-reinforcement Learning by Generative Language Models -- A Perspective","date":"2023-06-12","arxiv_id":"2306.07135","n_code_links":0,"syntology":null},{"paper":"/paper/pruning-meets-low-rank-parameter-efficient","title":"LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning","date":"2023-05-28","arxiv_id":"2305.18403","n_code_links":1,"syntology":{"ran":0,"of":5,"unverified":5,"pointer_only":0}}],"papers_shown":30,"tasks":[{"task":"/task/regression-1","name":"regression","papers":7},{"task":"/task/language-modelling","name":"Language Modelling","papers":6},{"task":"/task/language-modeling","name":"Language Modeling","papers":5},{"task":"/task/quantization","name":"Quantization","papers":3},{"task":"/task/denoising","name":"Denoising","papers":2},{"task":"/task/diversity","name":"Diversity","papers":2},{"task":"/task/large-language-model","name":"Large Language Model","papers":2},{"task":"/task/question-answering","name":"Question Answering","papers":2},{"task":"/task/retrieval","name":"Retrieval","papers":2},{"task":"/task/retrieval-augmented-generation","name":"Retrieval-augmented Generation","papers":2},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":2},{"task":"/task/model","name":"model","papers":2},{"task":"/task/parameter-estimation","name":"parameter estimation","papers":2},{"task":"/task/parameter-efficient-fine-tuning","name":"parameter-efficient fine-tuning","papers":2},{"task":"/task/adversarial-robustness","name":"Adversarial Robustness","papers":1},{"task":"/task/causal-discovery","name":"Causal Discovery","papers":1},{"task":"/task/chatbot","name":"Chatbot","papers":1},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/conformal-prediction","name":"Conformal Prediction","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1}],"tasks_shown":20,"n_tasks":63,"usage_by_year":[{"year":"2022","papers":7},{"year":"2023","papers":25},{"year":"2024","papers":8},{"year":"2025","papers":6}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/glm"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}