14 citations · 31 across the 27 of their papers we have counts for
17 papers · 1 filter
Synthetic Pre-Pre-Training Improves Language Model Robustness to Noisy Pre-Training Data
Xu Guo, Runyu Peng, Jian Tong +4
Large language models (LLMs) rely on web-scale corpora for pre-training. The noise inherent in these datasets tends to obscure meaningful patterns and ultimately degrade model perf…
Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment
Yuming Yang, Mingyoung Lai, Wanxu Zhao +13
Long chain-of-thought (CoT) trajectories provide rich supervision signals for distilling reasoning from teacher to student LLMs. However, both prior work and our experiments show t…
Evolution of Concepts in Language Model Pre-Training
Xuyang Ge, Wentao Shu, Jiaxing Wu +3
Language models obtain extensive capabilities through pre-training. However, the pre-training process remains a black box. In this work, we track linear interpretable feature evolu…
Pre-Trained Policy Discriminators are General Reward Models
Shihan Dou, Shichun Liu, Yuming Yang +19
We offer a novel perspective on reward modeling by formulating it as a policy discriminator, which quantifies the difference between two policies to generate a reward signal, guidi…
Capability Salience Vector: Fine-grained Alignment of Loss and Capabilities for Downstream Task Scaling Law
Qiming Ge, Shuhao Xing, Songyang Gao +8
Scaling law builds the relationship between training computation and validation loss, enabling researchers to effectively predict the loss trending of models across different level…
GAOKAO-Eval: Does high scores truly reflect strong capabilities in LLMs?
Zhikai Lei, Tianyi Liang, Hanglei Hu +8
Large Language Models (LLMs) are commonly evaluated using human-crafted benchmarks, under the premise that higher scores implicitly reflect stronger human-like performance. However…
Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures
Junxuan Wang, Xuyang Ge, Wentao Shu +4
The hypothesis of Universality in interpretability suggests that different neural networks may converge to implement similar algorithms on similar tasks. In this work, we investiga…
BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments
Xinghao Wang, Pengyu Wang, Bo Wang +3
Large language models (LLMs) have revolutionized numerous applications, yet their deployment remains challenged by memory constraints on local devices. While scaling laws have enha…
Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance
Jiasheng Ye, Peiju Liu, Tianxiang Sun +3
Pretraining data of large language models composes multiple domains (e.g., web texts, academic papers, codes), whose mixture proportions crucially impact the competence of outcome…
Code Needs Comments: Enhancing Code LLMs with Comment Augmentation
Demin Song, Honglin Guo, Yunhua Zhou +8
The programming skill is one crucial ability for Large Language Models (LLMs), necessitating a deep understanding of programming languages (PLs) and their correlation with natural…
Data-free Weight Compress and Denoise for Large Language Models
Runyu Peng, Yunhua Zhou, Qipeng Guo +4
Large Language Models (LLMs) are reshaping the research landscape in artificial intelligence, particularly as model parameters scale up significantly, unlocking remarkable capabili…
AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling
Jun Zhan, Junqi Dai, Jiasheng Ye +13
We introduce AnyGPT, an any-to-any multimodal language model that utilizes discrete representations for the unified processing of various modalities, including speech, text, images…
DenoSent: A Denoising Objective for Self-Supervised Sentence Representation Learning
Xinghao Wang, Junliang He, Pengyu Wang +3
Contrastive-learning-based methods have dominated sentence representation learning. These methods regularize the representation space by pulling similar sentence representations cl…
Discovering New Intents Using Latent Variables
Yunhua Zhou, Peiju Liu, Yuxin Wang +1
Discovering new intents is of great significance to establishing Bootstrapped Task-Oriented Dialogue System. Most existing methods either lack the ability to transfer prior knowled…
The Open-World Lottery Ticket Hypothesis for OOD Intent Classification
Yunhua Zhou, Pengyu Wang, Peiju Liu +2
Most existing methods of Out-of-Domain (OOD) intent classification rely on extensive auxiliary OOD corpora or specific training paradigms. However, they are underdeveloped in the u…
BBTv2: Towards a Gradient-Free Future with Large Language Models
Tianxiang Sun, Zhengfu He, Hong Qian +3
Most downstream adaptation methods tune all or part of the parameters of pre-trained models (PTMs) through gradient descent, where the tuning cost increases linearly with the growt…
Early Exiting with Ensemble Internal Classifiers
Tianxiang Sun, Yunhua Zhou, Xiangyang Liu +5
As a simple technique to accelerate inference of large-scale pre-trained models, early exiting has gained much attention in the NLP community. It allows samples to exit early at in…