Search Results for author:
Found 17 papers, 11 papers with code
Overtrained Language Models Are Harder to Fine-Tune
Large language models are pre-trained on ever-growing token budgets under the assumption that better pre-training performance translates to improved downstream models.
Metadata Conditioning Accelerates Language Model Pre-training
The vast diversity of styles, domains, and quality levels present in language model pre-training corpora is essential in developing general model capabilities, but efficiently learning and deploying the correct behaviors exemplified in each of these heterogeneous data sources is challenging.
Provable unlearning in topic modeling and downstream tasks
Machine unlearning algorithms are increasingly important as legal concerns arise around the provenance of training data, but verifying the success of unlearning is often difficult.
Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws
The composition of pretraining data is a key determinant of foundation models' performance, but there is no standard guideline for allocating a limited computational budget across different data sources.
Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
Direct Preference Optimization (DPO) and its variants are increasingly used for aligning language models with human preferences.
Progressive distillation induces an implicit curriculum
Our theoretical and empirical findings on sparse parity, complemented by empirical observations on more complex tasks, highlight the benefit of progressive distillation via implicit curriculum across setups.
MUSE: Machine Unlearning Six-Way Evaluation for Language Models
Data owners may request the removal of their data from a trained model due to privacy or copyright concerns.
CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs
All models lag far behind human performance of 80. 5%, underscoring weaknesses in the chart understanding capabilities of existing MLLMs.
Preference Learning Algorithms Do Not Learn Preference Rankings
Preference learning algorithms (e. g., RLHF and DPO) are frequently used to steer LLMs to produce generations that are more preferred by humans, but our understanding of their inner workings is still limited.
LESS: Selecting Influential Data for Targeted Instruction Tuning
Instruction tuning has unlocked powerful capabilities in large language models (LLMs), effectively using combined datasets to develop generalpurpose chatbots.
The Marginal Value of Momentum for Small Learning Rate SGD
Momentum is known to accelerate the convergence of gradient descent in strongly convex settings without stochastic gradient noise.
Trainable Transformer in Transformer
In this work, we propose an efficient construction, Transformer in Transformer (in short, TinT), that allows a transformer to simulate and fine-tune complex models internally during inference (e. g., pre-trained language models).
Fine-Tuning Language Models with Just Forward Passes
Fine-tuning language models (LMs) has yielded success on diverse downstream tasks, but as LMs grow in size, backpropagation requires a prohibitively large amount of memory.
A Kernel-Based View of Language Model Fine-Tuning
It has become standard to solve NLP tasks by fine-tuning pre-trained language models (LMs), especially in low-data settings.
On the SDEs and Scaling Rules for Adaptive Gradient Algorithms
Approximating Stochastic Gradient Descent (SGD) as a Stochastic Differential Equation (SDE) has allowed researchers to enjoy the benefits of studying a continuous optimization trajectory while carefully preserving the stochasticity of SGD.
On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)
It is generally recognized that finite learning rate (LR), in contrast to infinitesimal LR, is important for good generalization in real-life deep nets.
A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks
This paper initiates a mathematical study of this phenomenon for the downstream task of text classification by considering the following questions: (1) What is the intuitive connection between the pretraining task of next word prediction and text classification?
