This paper enhances language models with knowledge awareness.
problem Understanding how much knowledge pretrained language models grasp.
method Inserting explicit knowledge layers into pretraining without changing transformer architecture.
result Significantly more knowledge packed into transformer parameters.
New study finds best language model architecture and pretraining objective for zero-shot tasks.
problem Evaluating which language model architectures and pretraining objectives best enable zero-shot generalization.
method Compared three model architectures and two pretraining objectives across 170 billion tokens, with and without finetuning.
result Causal decoder-only models trained on autoregressive language modeling exhibit strongest zero-shot generalization.
CERT improves language understanding by contrastively learning sentence-level semantics.
problem Lack of sentence-level semantics in existing pretraining tasks.
method Contrastive self-supervised learning at the sentence level using back-translation augmentations.
result CERT outperforms BERT on 7 out of 11 GLUE benchmark tasks, achieving the same performance as BERT on 2 tasks.
Transformer models can solve complex math problems with less data.
problem Solving complex symbolic mathematics problems with limited data.
method Pretrain transformer models on language translation tasks and fine-tune for symbolic math.
result Pretrained transformer models achieve comparable accuracy to state-of-the-art models with less data.
In natural language processing, it has been observed recently that generalization could be greatly improved by finetuning a large-scale language model pretrained on a large unlabeled corpus. Despite its recent success and wide adoption, finetuning a large pretrained language model on a downstream task is prone to degen…
This study examines how the size and alignment of pretraining data affect the performance of large language models on downstream tasks.
problem Understanding how the size and alignment of pretraining data impact the performance of large language models on downstream tasks.
method Investigated the scaling behavior of large language models in a transfer learning setting, focusing on machine translation tasks.
result The size of the finetuning dataset and the distribution alignment between pretraining and downstream data significantly influence the scaling behavior of downstream performance.
The ever-growing volume of data of user-generated content on social media provides a nearly unlimited corpus of unlabeled data even in languages where resources are scarce. In this paper, we demonstrate that state-of-the-art results on two Thai social text categorization tasks can be realized by pretraining a language …
Synthetic continued pretraining enhances model performance with synthetic data.
problem Data inefficiency in pretrained models when adapting to domain-specific documents.
method Synthetic data augmentation using EntiGraph to create a large synthetic corpus.
result Language models can answer questions and follow instructions without access to domain-specific documents.
Unified framework for ICL in causal and masked models.
problem Understanding ICL in masked language models and comparing it to causal models.
method Developed a statistical learning framework representing context by empirical measure and predicting using context and query.
result Upper bounds for masked and autoregressive objectives under Wasserstein-type regularity conditions.
New research reveals how the pretraining distribution affects in-context learning in large language models.
problem Understanding how the pretraining distribution influences in-context learning in large language models.
method Developed a theoretical framework to characterize the relationship between pretraining distribution properties and in-context learning performance.
result Characterized a fundamental trade-off between robust task selection and generalization in ICL due to the pretraining distribution's statistical properties.
Paper introduces a multi-stage influence function to track model predictions.
problem Improving natural language processing and computer vision performance.
method Develops a multi-stage influence function to track predictions from finetuned models back to pretraining data.
result Identifies pretraining examples contributing most to finetuning task predictions.
Plex improves model reliability across vision and language tasks.
problem Improving model reliability in diverse decision-making tasks involving uncertainty and adaptation.
method Developed ViT-Plex and T5-Plex pretrained model extensions to evaluate and improve reliability across 40 datasets.
result Plex greatly improves state-of-the-art across reliability tasks, simplifying evaluation and performance.
Analysis of pretrained models' effectiveness in downstream tasks.
problem Understanding why pretrained models perform well in NLP tasks.
method Analyzed head and prompt tuning approaches using latent variable models.
result Prompt tuning provides stronger guarantees than head tuning.
A new approach to protein language models combines latent space prediction with masked language modeling.
problem Improving protein language models by predicting amino acid identities at masked positions.
method A variant of masked language modeling that predicts latent targets only at masked positions, retaining the MLM cross-entropy.
result The new approach outperforms pure masked language modeling on 11 out of 16 downstream tasks.
Universal Language Model for Fine-tuning [arXiv:1801.06146] (ULMFiT) is one of the first NLP methods for efficient inductive transfer learning. Unsupervised pretraining results in improvements on many NLP tasks for English. In this paper, we describe a new method that uses subword tokenization to adapt ULMFiT to langua…
Theoretical analysis of data quality and synergies in LLMs.
problem Understanding why different training methods require different amounts of data.
method Theoretical analysis of transformers trained on a weight prediction task for linear regression.
result SFT excels on smaller datasets challenging for the pretrained model, while RL benefits from large, not overly difficult data.
DatedGPT prevents lookahead bias in financial forecasting models.
problem Lookahead bias in large language models trained on internet-scale data.
method Time-aware pretraining with annual data cutoffs and instruction fine-tuning.
result Models' knowledge is effectively bounded by their data cutoff year, improving forecasting validity.
Language models help text classification tasks by predicting next words.
problem Lack of theoretical understanding of why language models perform well on downstream tasks.
method Mathematical study of the connection between next word prediction and text classification, formalizing it and quantifying the benefit.
result Language models that are ε-optimal in cross-entropy learn features that can solve classification tasks with linear approximation.
A new method uses a frozen language model to improve sample efficiency in reinforcement learning.
problem Improving sample efficiency in reinforcement learning with partially observable environments.
method FROZEN Hopfield network and HELM (History Embedding Language Model) method.
result HELM achieves new state-of-the-art results on Minigrid and Procgen environments.
New framework selects high-quality pretraining data without training LLMs.
problem Slow progress in understanding pretraining data due to costly experiments.
method Statistical framework based on perplexity-benchmark correlations.
result Approach outperforms existing methods on multiple benchmarks.
Pretraining models improves text classification accuracy, but diminishing returns are observed with large datasets.
problem Improving text classification accuracy with pretrained models.
method Examined the benefits of pretrained models on text classification tasks with varying amounts of training data.
result As the number of training examples grows into the millions, the accuracy gap between pretrained BERT-based models and vanilla LSTM narrows to within 1%.
Transformers can learn new tasks from diverse pretraining data but struggle with out-of-domain tasks.
problem Transformer models' ability to learn new tasks in-context is limited by their pretraining data coverage.
method Investigation of transformer models trained on (x,f(x)) pairs, comparing in-context learning capabilities across different task families. result Transformers can identify and learn within task families in their pretraining data but fail with out-of-domain tasks.
A pretrained LLM and its finetuned version can detect OOD data effectively.
problem Detecting out-of-distribution data in language models.
method Using the likelihood ratio between a pretrained and finetuned LLM.
result The likelihood ratio is an effective criterion for OOD detection.
The study introduces anytime learning schedules for large language models without fixed horizons.
problem Training large language models without knowing the total training horizon.
method Theoretical analysis and weight averaging to create anytime learning schedules.
result Theoretical and empirical evidence shows that weight averaging with simple step sizes can achieve comparable final loss to well-tuned cosine schedules.
FinPT uses large pretrained models to predict financial risks.
problem Outdated algorithms and lack of open financial benchmarks.
method Profile Tuning on large pretrained foundation models.
result Demonstrated effectiveness on FinBench datasets.
AFTER technique improves NLP models by preventing overfitting to task-specific domains.
problem Standard fine-tuning degrades pretraining domain representations.
method Complements task-specific loss with adversarial objective.
result AFTER leads to improved performance on various NLP tasks.
PMI-Masking improves MLM pretraining by masking correlated spans efficiently.
problem Uniform token masking leads to inefficient and suboptimal performance in MLMs.
method PMI-Masking uses Pointwise Mutual Information to mask n-grams with high collocation.
result PMI-Masking reaches half the training time and improves performance.
Funnel-Transformer reduces computation by compressing sequence data.
problem Redundant token-level representations in language processing.
method Gradually compresses sequence of hidden states to a shorter one.
result Funnel-Transformer outperforms standard Transformer with fewer FLOPs.
SFAVEL distills features from language models for fact verification without annotations.
problem Fact verification with semantically meaningful and compact features.
method Self-supervised pretraining using contrastive loss with language models.
result Achieved state-of-the-art results on FB15k-237 and FEVER.
Method constructs finance LLMs without instruction data using pretraining and model merging.
problem Developing domain-specific LLMs for finance is resource-intensive.
method Continual pretraining on financial data + model merging of instruction-tuned and domain-specific pretrained vectors.
result Successfully constructs instruction-tuned LLMs for finance without additional instruction data.
New model uses pretrained biochemical language models to generate drug compounds.
problem Developing novel compounds targeting specific proteins.
method Exploits pretrained language models to initialize and fine-tune targeted molecule generation models.
result Warm-started models outperform baseline models, with one-stage strategy showing better generalization.
ATD measures language distance using neural models, recovering linguistic groupings.
problem Lack of a unified quantitative measure for cross-linguistic distance.
method Pretrained multilingual language models, attention mechanisms, optimal transport.
result ATD quantifies representational distance between languages, recovering linguistic groupings.
This study examines how large language models learn in-context and provides insights into their performance and architecture.
problem Understanding how large language models learn in-context and their performance metrics.
method Bayesian model averaging, parameterization, and statistical analysis of transformer architecture.
result Transformer architecture enables in-context learning through attention mechanisms and fine-grained statistical analysis.
Pretrained masked language models (MLMs) require finetuning for most NLP tasks. Instead, we evaluate MLMs out of the box via their pseudo-log-likelihood scores (PLLs), which are computed by masking tokens one by one. We show that PLLs outperform scores from autoregressive language models like GPT-2 in a variety of task…
The paper studies how search and distillation improve reasoning in large language models.
problem Improving reasoning capabilities of large language models.
method Viewing chain-of-thought generation as a metastable Markov process, proving benefits of search and distillation.
result Search protocol rewards sparse edges, reducing the expected number of steps to reach different clusters.
We present BART, a denoising autoencoder for pretraining sequence-to-sequence models. BART is trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text. It uses a standard Tranformer-based neural machine translation architecture which, despite its simpl…
Data selection boosts fact memorization in language models.
problem Language models struggle to accurately memorize factual knowledge.
method Formalizes fact memorization, proposes data selection schemes based on training loss.
result Data selection boosts fact accuracy to model capacity and improves performance.
Clinical notes in electronic health records contain highly heterogeneous writing styles, including non-standard terminology or abbreviations. Using these notes in predictive modeling has traditionally required preprocessing (e.g. taking frequent terms or topic modeling) that removes much of the richness of the source d…
Bias correction improves language model training performance.
problem Stochastic update bias in preconditioned optimizers.
method Cross-fitted preconditioning and variance-corrected inversion.
result Reduces held-out pretraining loss by 0.15 nats.
GAPA method provides efficient uncertainty quantification for pretrained networks.
problem Reliable uncertainty estimates for pretrained models are challenging.
method Post-hoc Gaussian Process Activations (GAPA) method that shifts Bayesian modeling from weights to activations.
result GAPA method provides efficient uncertainty quantification without altering the backbone's predictions.
New pruning method retains model expressiveness for NLP tasks.
problem Pruning large pretrained transformer models for real-world deployment.
method Mixture Gaussian Prior Pruning (MGPP) algorithm.
result MGPP outperforms existing pruning methods in high sparsity settings.
NoLBERT avoids lookback and lookahead biases for better econometric inference.
problem Information leakage in language models affects econometric inference.
method Pretrained on text from 1976-1995, avoiding lookback and lookahead biases.
result NoLBERT outperforms domain-specific baselines and predicts higher profit growth.
Hi-RES framework extracts medical relations from articles and EHRs.
problem Manual annotation bottleneck in relation extraction.
method Labeling sentences, creating improved negative samples, using pretrained language models, and combining EHR embeddings.
result Significant accuracy increases in relation extraction, up to 0.998 for disorder-location relations.
Inductive transfer learning has greatly impacted computer vision, but existing approaches in NLP still require task-specific modifications and training from scratch. We propose Universal Language Model Fine-tuning (ULMFiT), an effective transfer learning method that can be applied to any task in NLP, and introduce tech…
Model forgets examples; this research predicts which ones to replay.
problem Language models forget examples during updates, leading to errors.
method Train forecasting models to predict which examples will be forgotten.
result Forecasting models can reduce forgetting of upstream pretraining examples.
Prior work in visual dialog has focused on training deep neural models on VisDial in isolation. Instead, we present an approach to leverage pretraining on related vision-language datasets before transferring to visual dialog. We adapt the recently proposed ViLBERT (Lu et al., 2019) model for multi-turn visually-grounde…
This study compares transfer learning and self-supervised learning for better model performance.
problem Choosing between transfer learning and self-supervised learning for optimal model performance.
method Comprehensive comparative study of transfer learning and self-supervised learning under various data and task properties.
result Self-supervised learning outperforms transfer learning in certain applications, and vice versa.
Adaptive batch size schedules improve language model training efficiency and generalization.
problem Dilemma of choosing batch sizes in large-scale model training.
method General-purpose adaptive batch size schedules compatible with data and model parallelism.
result Adaptive batch size schedules outperform constant batch sizes and heuristic warmup schedules.