Challenge: a large body of work has examined the training dynamics of language models.
Approach: They investigate the convergence of language models (LMs) trained under different random seeds . they find that larger models reconverge faster in later training stages, while smaller models never actually reconverge.
Outcome: The proposed model size and training checkpoints influence convergence of language models under different seeds.

Similar Papers

Establishing a Scale for Kullback-Leibler Divergence in Language Models Across Various Settings (2026.findings-acl)

Copied to clipboard

Challenge: Fig. 1 and 2 shows that log-likelihood vectors provide a consistent representation for language models . weight permutation symmetries and architectural dependencies hinder direct comparisons between models with different learning methods or designs.
Approach: They propose a log-likelihood vector for comparing language models as probability distributions . they establish a consistent scale for KL divergence across various settings .
Outcome: The proposed model comparisons show that the log-likelihood space is smaller than the weight space . the proposed model compares language models across checkpoints, model sizes, quantization, fine-tuning, and layers .
Do language models accommodate their users? A study of linguistic convergence (2026.eacl-long)

Copied to clipboard

Challenge: In this paper, we examine how large language models adapt their language use to the linguistic patterns of their user.
Approach: They examine whether large language models exhibit linguistic convergence, a pragmatic element of human language communication, and compare their results to original human responses.
Outcome: The proposed model language use is significantly different from that of humans.
Recent Advances in Pre-trained Language Models: Why Do They Work and How Do They Work (2022.aacl-tutorials)

Copied to clipboard

Challenge: Pre-trained language models are language models that are pre-taught on large-scaled corpora in a self-supervised fashion.
Approach: This tutorial provides a broad and comprehensive introduction to pre-trained language models . it focuses on emerging methods that enable PLMs to perform diverse downstream tasks .
Outcome: This tutorial focuses on the benefits of pre-trained language models and how to use them in NLP tasks.
Tending Towards Stability: Convergence Challenges in Small Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Increasing the number of parameters in language models is a common strategy to enhance performance, but smaller models often underperform compared to their larger counterparts due to their reduced representational capacity.
Approach: They use the Pythia model suite to analyse the training dynamics that underlie this phenomenon.
Outcome: The proposed model suite enables us to examine the training dynamics of small models.
Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods to detect text in training corpus are limited due to their low token probabilities.
Approach: They propose a method to calibrate token probabilities for pretraining data detection by using a divergence-based calibration method.
Outcome: The proposed method significantly outperforms existing methods on Chinese text on English-language benchmarks and patents.
Learning Is Not A Race: Improving Retrieval in Language Models via Equal Learning (2025.findings-emnlp)

Copied to clipboard

Challenge: Overparametrized models trained on cross-entropy loss can overfit on noise . Fitting some tokens early reduces gradient signals in later iterations .
Approach: They propose to overfit models trained on cross-entropy loss on noise . fitting some tokens early reduces gradient signals in later iterations .
Outcome: The proposed approaches can be applied to large language models with longer contexts or larger embedding sizes.
A Distributional Perspective on Word Learning in Neural Language Models (2025.naacl-long)

Copied to clipboard

Challenge: Language models are increasingly being studied as models of human language learners.
Approach: They propose a distributional approach to word learning that captures distributional knowledge and gradient preferences for the word’s appropriateness.
Outcome: The proposed signatures capture knowledge of where the target word can and cannot occur as well as gradient preferences about the word’s appropriateness.
Training Trajectories of Language Models Across Scales (2023.acl-long)

Copied to clipboard

Challenge: Scaling up language models has led to unprecedented performance gains, but little is understood about how the training dynamics change as models get larger.
Approach: They analyze the training checkpoints of different-sized OPT models on next-token prediction, sequence-level generation and downstream tasks.
Outcome: The results show that language models of different sizes learn more during training . small models halt at hallucinations, larger ones learn to assign lower probabilities .
Experimenting with Power Divergences for Language Modeling (D19-1)

Copied to clipboard

Challenge: Language models are an important component in many NLP tasks, where they provide prior knowledge on the language used.
Approach: They propose to use power divergences to prioritize learning on frequent or rare words . they use a sample-based objective to approximate a softmax and noise-constrained estimate .
Outcome: The proposed power divergences can be used to prioritize learning on the frequent or rare words and lead to general performance improvements.
Distribution Prompting: Understanding the Expressivity of Language Models Through the Next-Token Distributions They Can Produce (2025.emnlp-main)

Copied to clipboard

Challenge: Autoregressive neural language models (LMs) generate a probability distribution over tokens at each time step given a prompt.
Approach: They propose to find a prompt that induces LMs to output a distribution as close as possible to the target, using either soft or hard gradient-based prompt tuning.
Outcome: The proposed model is able to generate a distribution as close as possible to a target given a prompt, and it can be used to approximate distributions with low or high entropy.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations