1.1k citations · 2.4k across the 37 of their papers we have counts for
26 papers · 1 filter
WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning
Zehan Qi, Xiao Liu, Iat Long Iong +11
Large language models (LLMs) have shown remarkable potential as autonomous agents, particularly in web-based tasks. However, existing LLM web agents heavily rely on expensive propr…
ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools
Team GLM, :, Aohan Zeng +56
We introduce ChatGLM, an evolving family of large language models that we have been developing over time. This report primarily focuses on the GLM-4 language series, which includes…
NaturalCodeBench: Examining Coding Performance Mismatch on HumanEval and Natural User Prompts
Shudan Zhang, Hanlin Zhao, Xiao Liu +6
Large language models (LLMs) have manifested strong ability to generate codes for productive activities. However, current benchmarks for code synthesis, such as HumanEval, MBPP, an…
ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline
Yifan Xu, Xiao Liu, Xinghan Liu +9
Large language models (LLMs) have shown excellent mastering of human language, but still struggle in real-world applications that require mathematical problem-solving. While many s…
ChatGLM-RLHF: Practices of Aligning Large Language Models with Human Feedback
Zhenyu Hou, Yilin Niu, Zhengxiao Du +8
ChatGLM is a free-to-use AI service powered by the ChatGLM family of large language models (LLMs). In this paper, we present the ChatGLM-RLHF pipeline -- a reinforcement learning f…
AutoWebGLM: A Large Language Model-based Web Navigating Agent
Hanyu Lai, Xiao Liu, Iat Long Iong +8
Large language models (LLMs) have fueled many intelligent web agents, but most existing ones perform far from satisfying in real-world web navigation tasks due to three factors: (1…
Extensive Self-Contrast Enables Feedback-Free Language Model Alignment
Xiao Liu, Xixuan Song, Yuxiao Dong +1
Reinforcement learning from human feedback (RLHF) has been a central technique for recent large language model (LLM) alignment. However, its heavy dependence on costly human or LLM…
Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments
Yu Gu, Yiheng Shu, Hao Yu +6
The applications of large language models (LLMs) have expanded well beyond the confines of text processing, signaling a new era where LLMs are envisioned as generalist agents capab…
AlignBench: Benchmarking Chinese Alignment of Large Language Models
Xiao Liu, Xuanyu Lei, Shengyuan Wang +15
Alignment has become a critical step for instruction-tuned Large Language Models (LLMs) to become helpful assistants. However, the effective evaluation of alignment for emerging Ch…
Black-Box Prompt Optimization: Aligning Large Language Models without Model Training
Jiale Cheng, Xiao Liu, Kehan Zheng +5
Large language models (LLMs) have shown impressive success in various applications. However, these models are often not well aligned with human intents, which calls for additional…
AgentTuning: Enabling Generalized Agent Abilities for LLMs
Aohan Zeng, Mingdao Liu, Rui Lu +4
Open large language models (LLMs) with great performance in various tasks have significantly advanced the development of LLMs. However, they are far inferior to commercial models s…
SafetyBench: Evaluating the Safety of Large Language Models
Zhexin Zhang, Leqi Lei, Lindong Wu +7
With the rapid development of Large Language Models (LLMs), increasing attention has been paid to their safety concerns. Consequently, evaluating the safety of LLMs has become an e…
LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
Yushi Bai, Xin Lv, Jiajie Zhang +10
Although large language models (LLMs) demonstrate impressive performance for many language tasks, most of them can only handle texts a few thousand tokens long, limiting their appl…
WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferences
Xiao Liu, Hanyu Lai, Hao Yu +6
We present WebGLM, a web-enhanced question-answering system based on the General Language Model (GLM). Its goal is to augment a pre-trained large language model (LLM) with web sear…
Revisiting Parallel Context Windows: A Frustratingly Simple Alternative and Chain-of-Thought Deterioration
Kejuan Yang, Xiao Liu, Kaiwen Men +3
We identify two crucial limitations in the evaluation of recent parallel-integrated method Parallel Context Windows (PCW), which extends the maximum context lengths of language mod…
IELM: An Open Information Extraction Benchmark for Pre-Trained Language Models
Chenguang Wang, Xiao Liu, Dawn Song
We introduce a new open information extraction (OIE) benchmark for pre-trained language models (LM). Recent studies have demonstrated that pre-trained LMs, such as BERT and GPT, ma…
GLM-130B: An Open Bilingual Pre-trained Model
Aohan Zeng, Xiao Liu, Zhengxiao Du +15
We introduce GLM-130B, a bilingual (English and Chinese) pre-trained language model with 130 billion parameters. It is an attempt to open-source a 100B-scale model at least as good…
Parameter-Efficient Prompt Tuning Makes Generalized and Calibrated Neural Text Retrievers
Weng Lam Tam, Xiao Liu, Kaixuan Ji +6
Prompt tuning attempts to update few task-specific parameters in pre-trained models. It has achieved comparable performance to fine-tuning of the full parameter set on both languag…
DeepStruct: Pretraining of Language Models for Structure Prediction
Chenguang Wang, Xiao Liu, Zui Chen +3
We introduce a method for improving the structural understanding abilities of language models. Unlike previous approaches that finetune the models with task-specific augmentation,…
P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks
Xiao Liu, Kaixuan Ji, Yicheng Fu +4
Prompt tuning, which only tunes continuous prompts with a frozen language model, substantially reduces per-task storage and memory usage at training. However, in the context of NLU…
Zero-Shot Information Extraction as a Unified Text-to-Triple Translation
Chenguang Wang, Xiao Liu, Zui Chen +3
We cast a suite of information extraction tasks into a text-to-triple translation framework. Instead of solving each task relying on task-specific datasets and models, we formalize…
A Self-supervised Method for Entity Alignment
Xiao Liu, Haoyun Hong, Xinghao Wang +4
Entity alignment, aiming to identify equivalent entities across different knowledge graphs (KGs), is a fundamental problem for constructing large-scale KGs. Over the course of its…
GPT Understands, Too
Xiao Liu, Yanan Zheng, Zhengxiao Du +4
Prompting a pretrained language model with natural language patterns has been proved effective for natural language understanding (NLU). However, our preliminary study reveals that…
GLM: General Language Model Pretraining with Autoregressive Blank Infilling
Zhengxiao Du, Yujie Qian, Xiao Liu +4
There have been various types of pretraining architectures including autoencoding models (e.g., BERT), autoregressive models (e.g., GPT), and encoder-decoder models (e.g., T5). How…