Language models are essential for natural language processing (NLP) tasks, such as machine translation and text summarization. Remarkable performance has been demonstrated recently across many NLP domains via a Transformer-based language model with over a billion parameters, verifying the benefits of model size. Model …
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,657 papers · 148 categories
Trend · papers per month
48 results for “Transformer-based language models”
A framework uses free probability to analyze Transformer models.
problem Understanding the dynamics and complexity of Transformer-based language models.
method Formal operator-theoretic analysis using free probability theory.
result Entropy-based generalization bounds derived under freeness assumptions.
Downscaled models outperform larger ones on GLUE tasks.
problem Difficulty in attributing performance changes to specific factors in large language models.
method Pre-trained down-scaled versions of Transformer-based architectures on a common corpus, benchmarked on GLUE tasks.
result MLM + NSP (BERT-style) consistently outperforms other objectives.
StonkBERT predicts stock price movements using company text data.
problem Can language models predict medium-run stock price movements?
method Fine-tuning transformer-based language models (BERT) on company text data (news articles, blogs, annual reports) for stock price performance classification.
result StonkBERT shows substantial improvement in predictive accuracy compared to traditional models, with news articles providing the best results.
We present an open-source tool for visualizing multi-head self-attention in Transformer-based language representation models. The tool extends earlier work by visualizing attention at three levels of granularity: the attention-head level, the model level, and the neuron level. We describe how each of these views can he…
Transformer models improve financial sentiment measurement.
problem Capturing nuanced sentiment from financial news articles.
method Transformer-based language models for sentiment classification and aggregation.
result Transformer models outperform traditional dictionary-based methods in sentiment classification.
BreakGPT predicts asset price surges using LLMs.
problem Predicting sharp upward movements in volatile financial markets.
method Adapts LLMs for time series forecasting, combining LLM capabilities with Transformer models.
result BreakGPT effectively captures local and global temporal dependencies.
GP-TS optimizes TLM pre-training hyperparameters efficiently.
problem Resource inefficiency in TLM pre-training.
method Bayesian optimization with Thompson sampling and Gaussian process.
result GP-TS achieves lower MLM loss in fewer epochs.
GPT-f uses language models to find new proofs in formal math.
problem Generating original mathematical terms for automated theorem proving.
method Transformer-based language model for automated theorem proving and proof assistant.
result GPT-f contributed new proofs to the Metamath library.
Study compares LSTM and Transformer models in financial time series prediction.
problem Comparing LSTM and Transformer models for financial time series prediction.
method Various LSTM-based and Transformer-based models compared on financial tasks; DLSTM and new Transformer architecture designed.
result Transformer-based models show limited advantage in absolute price sequence prediction, while LSTM-based models perform better on difference sequences.
Transformers forecast time series in-context, improving efficiency and performance.
problem Overfitting and limited performance in time series forecasting.
method Reformulate time series forecasting as input tokens, aligning with in-context learning mechanisms.
result Consistently better performance across various settings (full-data, few-shot, zero-shot).
LLMs are compared to Markov chains for natural language processing.
problem Theoretical analysis of LLMs' generalization capabilities.
method Equivalence between LLMs and Markov chains, studying multi-step inference.
result Derives generalization bounds for LLMs, capturing their behavior in practice.
Attentive Temporal Pooling for Conformer-based Streaming Language Identification in Long-form Speecheess.AS
Paper introduces a conformer-based system for streaming language identification in long-form speech.
problem Language identification in long-form audio.
method Conformer layers with attentive temporal pooling and domain adaptation.
result Conformer-based models significantly outperform LSTM and transformer models.
Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and, thus, are too resource-hungry and computation-intensive to suit low-capability devices or applications with strict latency re…
Transformer learns CoVaR from financial news, improving systemic risk forecasts.
problem Quantifying systemic financial risk using conditional Value-at-Risk (CoVaR).
method Transformer-based approach integrating financial news articles with market data.
result Transformer CoVaR improves out-of-sample forecasts and identifies market stress periods.
Recently, substantial progress has been made in language modeling by using deep neural networks. However, in practice, large scale neural language models have been shown to be prone to overfitting. In this paper, we present a simple yet highly effective adversarial training mechanism for regularizing neural language mo…
Biomedical research papers use significantly different language and jargon when compared to typical English text, which reduces the utility of pre-trained NLP models in this domain. Meanwhile Medline, a database of biomedical abstracts, introduces nearly a million new documents per-year. Applications that could benefit…
Enhances GNNs with text features for better fake news detection.
problem Detecting disinformation on social media using GNNs.
method Integrates Transformer-based textual features into GNNs.
result Contextual text representations improve GNN performance by 33.8% in Macro F1.
Transformer model for probabilistic dynamical systems.
problem Modeling high-dimensional dynamical systems from noisy observations.
method Parallel between dynamical systems and language modeling; transformer-based model with geometrical properties; iterative training algorithm.
result Fine-grid approximation of conditional probabilities for high-dimensional systems.
This paper analyzes speculative decoding, a method to speed up large language model inferences.
problem Theoretical understanding of speculative decoding is lacking.
method Conceptualizes speculative decoding as a markov chain problem and studies its key properties.
result Reveals fundamental connections between LLM components and their impact on decoding efficiency.
Models predict Alzheimer's Dementia from spontaneous speech with high accuracy.
problem Early diagnosis of Alzheimer's Dementia (AD) through spontaneous speech analysis.
method Compared natural language processing techniques including SVM, GBDT, CRFs, and Transformer-based models.
result Top models achieve 0.81-0.82 test set scores for AD vs controls and 4.58 RMSE for Mental Mini State Exam scores.
ACE models allow flexible conditioning and prediction of latent variables.
problem Lack of flexibility in conditioning and prediction of latent variables in probabilistic models.
method Introduces Amortized Conditioning Engine (ACE) that explicitly represents latent variables and allows runtime conditioning and prediction.
result ACE models outperform existing methods in diverse tasks like image completion, classification, Bayesian optimization, and simulation-based inference.
Neural dialogue models, despite their successes, still suffer from lack of relevance, diversity, and in many cases coherence in their generated responses. These issues can attributed to reasons including (1) short-range model architectures that capture limited temporal dependencies, (2) limitations of the maximum likel…
Algorithm improves query recommendations with immediate user feedback.
problem Lack of adaptability to immediate user feedback in query recommendation algorithms.
method Augmented transformer-based causal language models with multi-armed bandit framework.
result Substantial improvement in per-round regret compared to state-of-the-art models.
Model criticism tool evaluates text coherence and structure in generated long-form text.
problem Evaluate the high-level structure of generated text for coherence, coreference, and topicality.
method Apply model criticism in latent space to compare real and generated data distributions.
result Transformer-based models struggle with maintaining structural coherence and coreference.
Language models predict inorganic synthesis conditions and temperatures.
problem Limited data and heuristic approaches constrain inorganic synthesis planning.
method Language models without fine-tuning predict precursor conditions and temperatures.
result Language models achieve high accuracy in predicting synthesis conditions and temperatures.
Deep models learn to parse complex language structures from local data patterns.
problem Understanding how deep models parse and represent language structures.
method Introduced tunable probabilistic context-free grammars and a learning algorithm inspired by deep networks.
result Data correlations across scales enable hierarchical language representations.
Proposes EM-HRNN model for better hierarchical language representation.
problem Learning hierarchical representations in natural language processing.
method Introduces latent indicator layer and EM algorithm for training.
result EM-HRNN model outperforms other RNN-based models in document classification.
This study evaluates the robustness of transformation-based ensemble defense against evasion attacks.
problem Understanding the reasons behind the robustness improvement in transformation-based ensemble defense.
method Designing two adaptive attacks to evaluate transformation-based ensemble defense, conducting experiments to analyze robustness.
result The robustness improvement is mainly from irreversible transformations rather than the ensemble of models.
Neural networks using transformer-based architectures have recently demonstrated great power and flexibility in modeling sequences of many types. One of the core components of transformer networks is the attention layer, which allows contextual information to be exchanged among sequence elements. While many of the prev…
In this paper we investigate continuous speech recognition using electroencephalography (EEG) features using recently introduced end-to-end transformer based automatic speech recognition (ASR) model. Our results demonstrate that transformer based model demonstrate faster training compared to recurrent neural network (R…
Pre-training on different modalities improves Transformer performance in offline reinforcement learning.
problem Improving Transformer-based models for offline reinforcement learning tasks.
method Empirical investigation of pre-training on language and vision data, analysis of internal representations, and fine-tuning with no context.
result Pre-trained Transformers with language data can utilize context-like information to solve reinforcement learning tasks efficiently.
Many common sequential data sources, such as source code and natural language, have a natural tree-structured representation. These trees can be generated by fitting a sequence to a grammar, yielding a hierarchical ordering of the tokens in the sequence. This structure encodes a high degree of syntactic information, ma…
FinEAS models financial sentiment using BERT embeddings.
problem Financial sentiment analysis in markets.
method Supervised fine-tuning of BERT embeddings for financial texts.
result FinEAS outperforms vanilla BERT, LSTM, and FinBERT.
Transformer model predicts stock prices in Bangladesh's stock market.
problem Predicting volatile stock prices in the Bangladesh stock market.
method Transformer model applied to time series data for stock price prediction.
result Transformer model shows promising results in predicting stock price movements.
Paper investigates Lipschitz constants of self-attention modules in neural networks.
problem Lipschitz constants of self-attention modules in neural networks.
method Proved standard dot-product self-attention is not Lipschitz for unbounded input domain. Proposed L2 self-attention that is Lipschitz. Derived upper bound on L2 self-attention's Lipschitz constant.
result Proved standard self-attention is not Lipschitz for unbounded input domain and proposed an alternative L2 self-attention that is Lipschitz.
Recent Transformer-based contextual word representations, including BERT and XLNet, have shown state-of-the-art performance in multiple disciplines within NLP. Fine-tuning the trained contextual models on task-specific datasets has been the key to achieving superior performance downstream. While fine-tuning these pre-t…
FinAI-BERT classifies AI disclosures in financial reports with high accuracy.
problem Systematic detection of AI-related disclosures in financial reports.
method Fine-tuned transformer-based model on a curated dataset.
result Achieved near-perfect classification performance (99.37% accuracy).
Global Memory Augmentation (GMAT) improves Transformer performance on long documents.
problem Large memory requirements of Transformer pairwise dot-product attention for long sequences.
method Integrates a dense global memory of length M into sparse Transformer blocks.
result Significant improvement on various tasks, including synthetic tasks, masked language modeling, and reading comprehension.
Study evaluates five LLMs for financial report analysis, revealing performance differences and variability.
problem Lack of understanding in reliability, consistency, and transparency of LLMs in financial analysis.
method Human evaluation, automated similarity metrics, and behavioral diagnostics applied to five transformer-based LLMs over U.S. 10-K filings.
result No single LLM consistently dominates across all evaluation perspectives, highlighting variability and need for interpretability.
FiNCAT tool automatically identifies financial numerals in documents.
problem Differentiating between in-claim and out-of-claim numerals in financial documents.
method Extracts context embeddings of numerals using BERT, then uses Logistic Regression to classify.
result Achieved a Macro F1 score of 0.8223 on validation set.
Transformer models waste resources on long-context tasks.
problem Redundant attention computations in Transformer models for long-context tasks.
method Reformulate sequence modeling as supervised learning, analyze attention sparsity, formulate attention optimization as linear coding problem, propose Dynamic Group Attention.
result DGA reduces computational costs while maintaining performance.
Token-adaptive FFN design improves LLM expressivity.
problem Fixed activation functions limit FFN expressivity in LLMs.
method Mixture of Activations (MoA) and learnable activations (LA).
result MoA achieves lower terminal loss and better scaling than baselines.
Transformer with self-attention has achieved great success in the area of nature language processing. Recently, there have been a few studies on transformer for end-to-end speech recognition, while its application for hybrid acoustic model is still very limited. In this paper, we revisit the transformer-based hybrid ac…
LoLCATs improves linearized LLM quality with less memory and compute.
problem Linearizing large language models (LLMs) often degrades model quality and requires expensive training.
method Two-step method: attention transfer and low-rank adaptation.
result Significant improvement in linearizing quality with 20+ points on 5-shot MMLU.
This paper investigates efficient Transformers and finds they scale with problem size.
problem Finding suitable replacements for standard Transformers in large-scale tasks.
method Modeling efficient Transformers (Sparse and Linear) as Dynamic Programming problems and analyzing their reasoning capabilities.
result Efficient Transformers scale with problem size, but can be more efficient for certain DP problems.
Efficient algorithm finds fast Transformer models.
problem Slow inference time of Transformer models.
method Decompose Transformer architecture into components, use sampling-based one-shot search.
result Achieved 10% to 30% speedup on pre-trained BERT and 70% on top of a previous state-of-the-art model.
Paper explores privacy in machine learning models using ICL.
problem Privacy in in-context learning models.
method Differentially private pretraining algorithm for linear attention heads.
result Characterizes privacy-accuracy trade-off for ICL in linear regression.