Gradient-trained embeddings select important tokens in text.
problem Understanding the theoretical structure of token embeddings.
method One-layer softmax attention model with gradient descent.
result Gradient-trained embeddings align with important tokens based on frequency.
Minimal token perturbations reveal how Transformer models process information.
problem Understanding information propagation in Transformer models for interpretability.
method Study of minimal token perturbations on embedding space.
result Rare tokens cause larger shifts, and input information mixes deeper.
Method reveals hidden token embeddings of large language models.
problem Understanding hidden token embeddings in large language models.
method Structured prompts to expose token input embeddings up to homeomorphism.
result Mathematical proof for generic LLMs shows effectiveness of method.
Byte-level machine translation outperforms embedding-based methods.
problem Improving machine translation without embedding layers.
method Replacing embedding layers with one-hot representations of bytes, and using decoder-input dropout.
result Byte-to-byte machine translation achieves BLEU scores comparable to character-level and subword-level models.
STRATA generates code adversarial examples efficiently without gradients.
problem Generating adversarial examples for code that retains functional meaning.
method Uses token frequency statistics to construct gradient-free adversarial examples.
result Empirically outperforms gradient-based methods with less information and effort.
Transformers learn to recall with non-orthogonal embeddings in realistic settings.
problem Understanding how transformers store and retrieve knowledge in practical scenarios.
method Analyzing a single-layer transformer with random embeddings trained on a token-retrieval task.
result Explicit formulas for the model's storage capacity reveal a multiplicative dependence on sample size, embedding dimension, and sequence length.
Law explains how LLMs learn to predict next tokens.
problem Understanding how LLMs process input data internally.
method Introduced a precise law governing token embeddings in LLMs.
result Each layer equally contributes to next-token prediction accuracy.
This study improves sentence embeddings from BERT models.
problem Capturing the underlying meaning of sentences using BERT models.
method Comprehensive review and testing of various sentence embedding extraction and refinement methods.
result Representation-shaping techniques significantly improve sentence embeddings from BERT-based and simple baseline models.
The paper explores how gradient descent trains associative memories, revealing oscillations and convergence issues.
problem Training dynamics of associative memories in overparameterized and underparameterized settings.
method Reduction to particle system dynamics, theory, and experiments.
result Oscillatory transitory regimes and benign loss spikes in overparameterized settings, suboptimal memorization in underparameterized settings.
Gradient descent biases linear models in next-token prediction towards data entropy.
problem Optimization bias in next-token prediction models.
method Analysis of gradient descent on linear models with sparse conditional distributions.
result Gradient descent selects parameters that equate token logits differences to log-odds in the data subspace.
RESTA defends LLMs against jailbreaking attacks by adding random noise to embeddings.
problem Vulnerability of LLMs to jailbreaking attacks that generate harmful outputs.
method Adds random noise to embedding vectors and aggregates during token generation.
result RESTA achieves superior robustness versus utility tradeoffs compared to baseline defenses.
Transformer models are compared to curved spacetime in General Relativity.
problem Understanding the geometric structure of Transformer models.
method Geometric analogy to General Relativity, focusing on attention and curvature effects.
result Transformer token embeddings exhibit curvature, affecting their evolution over layers.
Attention mechanism learns to focus on sparse tokens efficiently.
problem Detecting weak, rare, and sparsely located features in long sequences.
method Theoretical analysis and training of a single-layer attention classifier in a sparse-token classification model.
result A single-layer attention classifier can achieve vanishing test error with logarithmic signal strength growth, unlike linear classifiers requiring linear growth.
The study shows how to accurately estimate embedding vectors in high dimensions.
problem How to accurately estimate embedding vectors in high-dimensional spaces.
method A simple probability model and a variant of low-rank approximate message passing (AMP) method.
result The AMP approach enables precise predictions of the accuracy of the estimation in certain high-dimensional limits.
Transformers can predict new tokens based on any number of context tokens, approximating continuous mappings with fixed resources.
problem Handling an arbitrarily large number of context tokens in transformers.
method Mathematical analysis of transformer's expressivity using Wasserstein distance and continuous mappings.
result Deep transformers are universal and can approximate continuous in-context mappings to arbitrary precision, uniformly over compact token domains.
Given a state-of-the-art deep neural network text classifier, we show the existence of a universal and very small perturbation vector (in the embedding space) that causes natural text to be misclassified with high probability. Unlike images on which a single fixed-size adversarial perturbation can be found, text is of …
Model compression is essential for serving large deep neural nets on devices with limited resources or applications that require real-time responses. As a case study, a state-of-the-art neural language model usually consists of one or more recurrent layers sandwiched between an embedding layer used for representing inp…
EPSTE: A geometric token and deep learning approach to estimating transfer entropy in neuroimaging time series
problem Inferring directed interactions between neural systems from EEG and MEG
method Reframing TE estimation as a learnable problem operating on structured symbolic representations
result EPSTE achieves near-perfect recovery of ground-truth directed structure and significantly lower absolute error than the baseline
Embedding words in a vector space has gained a lot of attention in recent years. While state-of-the-art methods provide efficient computation of word similarities via a low-dimensional matrix embedding, their motivation is often left unclear. In this paper, we argue that word embedding can be naturally viewed as a rank…
NMIXX fine-tunes embeddings for finance, outperforming general models in Korean.
problem Financial embeddings struggle in low-resource languages like Korean.
method Fine-tuned with 18.8K triplets, hard negatives, and translations.
result NMIXX achieves gains of +0.10 on English FinSTS and +0.22 on KorFinSTS.
Learnable token perturbations boost extrapolation in LLMs.
problem Limited flexibility of current discrete perturbations in large language models.
method Learnable continuous latent vector transformations in embedding space, unbiased estimating equations, stochastic gradient descent optimization.
result Significant gains in out-of-domain settings over state-of-the-art methods.
Mathematical framework using Riemannian geometry for intelligence and consciousness.
problem Lack of a unified mathematical framework for intelligence and consciousness.
method Conceptualizes intelligence as tokens in a high-dimensional space, using Riemannian geometry to describe structure and dynamics.
result Integrates geometric concepts to offer a unified framework for intelligence and consciousness.
Transformer models align words through attention weights, closely approximating Optimal Transport.
problem Understanding the internal mechanism of transformer models in language processing.
method Empirical evidence and theoretical analysis of attention weights and their relation to Optimal Transport.
result Transformer models can simulate gradient descent on the dual of entropy-regularized OT problem, providing a theoretical foundation for token alignment.
LITE models improve query-document relevance with learnable late interactions.
problem Improving query-document relevance with lower latency and storage.
method Proposes learnable late-interaction models (LITE) that use factorized query and document embeddings followed by a learnable scorer.
result Empirically, LITE outperforms previous late-interaction models in re-ranking tasks.
The paper uncovers symmetries in large language models through layer-peeled optimization.
problem Understanding geometric structure in large language model weights and context embeddings.
method Constrained layer-peeled optimization program to analyze symmetries in next-token distributions.
result Symmetries in target next-token distributions are transferred to optimal model weights and context embeddings.
A new watermarking method corrects bias in language models using maximal coupling.
problem Correcting bias in language model token distributions.
method Maximal coupling to balance bias correction and text quality.
result Outperforms prior techniques in preserving text quality and detectability.
Timer-XL predicts multidimensional time series using a unified Transformer approach.
problem Unified time series forecasting across various tasks and contexts.
method Decoder-only Transformers with a universal TimeAttention mechanism and deft position embedding.
result State-of-the-art performance across multiple forecasting benchmarks.
New insights show embedding lengths correlate with semantic properties.
problem Contrastive embedding norms ignore embedding magnitudes but correlate with semantic properties.
method Formal theoretical framework and analysis of optimization dynamics.
result Embedding lengths encode semantic information as a byproduct of training.
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.
This paper improves continuous adversarial training for LLMs using in-context learning theory.
problem Efficiently defending large language models (LLMs) against jailbreak attacks.
method The paper presents a theoretical analysis of continuous adversarial training (CAT) for LLMs based on in-context learning (ICL) theory, proving a robust generalization bound and proposing an improved regularization term.
result The robust generalization bound explains why CAT can defend against jailbreak prompts and shows that LLM robustness is related to embedding matrix singular values.
The abundance of open-source code, coupled with the success of recent advances in deep learning for natural language processing, has given rise to a promising new application of machine learning to source code. In this work, we explore the use of a Siamese recurrent neural network model on Python source code to create …
Natural language processing has improved tremendously after the success of word embedding techniques such as word2vec. Recently, the same idea has been applied on source code with encouraging results. In this survey, we aim to collect and discuss the usage of word embedding techniques on programs and source code. The a…
A quantum model classifies financial sentiment by mapping text chunks to quantum circuits.
problem Classifying financial texts with high accuracy and preserving semantic information.
method Chunked diagrams are mapped to quantum circuits, with a Transformer encoder and type embeddings added for context.
result The hybrid model improves sentiment classification over a simple averaging baseline.
Neural sequence generation is typically performed token-by-token and left-to-right. Whenever a token is generated only previously produced tokens are taken into consideration. In contrast, for problems such as sequence classification, bidirectional attention, which takes both past and future tokens into consideration, …
Paper reduces vocabulary losslessly for language model cooperation.
problem Language models struggle to cooperate with different tokenizations.
method Established a theoretical framework for lossless vocabulary reduction.
result Efficiently converts models with different tokenizations to cooperate with maximal common vocabulary.
This research improves capital efficiency and impermanent loss in cryptocurrency markets using multi-token trading pools.
problem Poor impermanent loss and capital efficiency in automated market makers.
method Analysis and construction of a multi-token token proactive market maker (MPMM).
result MPMM shows better impermanent loss and capital efficiency than comparable market makers.
This study examines whether tokenized assets improve liquidity and finds significant differences across categories.
problem Improving liquidity for real-world assets through tokenization.
method Examined tokenized real-world assets using Ethereum-based data, measuring liquidity through turnover, active addresses, and active-month indicator.
result Gold-backed tokens show more persistent on-chain activity than Treasury and private-credit-related products, but asset value alone does not reliably predict liquidity.
Study examines revenue from scam tokens on Ethereum, revealing key characteristics and market factors.
problem Revenue from scam tokens on Ethereum blockchain.
method Empirical analysis of Uniswap, examining characteristics and market factors.
result Revenue from scam tokens is influenced by market economic factors and community engagement.
Blockchain-based exchanges adopt based on token pair volatility and personal use.
problem Token value loss and arbitrage issues in decentralized exchanges.
method Investigation of Automated Market Makers (AMMs) using transaction-level data.
result AMMs are adopted for high personal use or highly correlated token price movements.
Blockchain fan tokens boost sports fan engagement by 50%.
problem Low fan engagement in sports decisions.
method Analyzed 3,576 fan token polls to identify determinants of participation.
result Fan tokens engage 4,003 participants per poll, 50% of token holders.
There is rising interest in vector-space word embeddings and their use in NLP, especially given recent methods for their fast estimation at very large scale. Nearly all this work, however, assumes a single vector per word type ignoring polysemy and thus jeopardizing their usefulness for downstream tasks. We present an …
Paper introduces a method to assess liquidity risk in meme tokens using entity-linked address analysis.
problem High market volatility and vulnerability to manipulation in meme tokens.
method Multi-dimensional approach integrating fund flow analysis, behavioral similarity, and anomalous transaction detection.
result Significant disparities between apparent and actual liquidity in meme token markets.
Traditionally, many text-mining tasks treat individual word-tokens as the finest meaningful semantic granularity. However, in many languages and specialized corpora, words are composed by concatenating semantically meaningful subword structures. Word-level analysis cannot leverage the semantic information present in su…
DOS improves language model generation by considering inter-token dependencies.
problem Lack of sequence-level information and inter-token dependencies in existing decoding strategies.
method Dependency-Oriented Sampler (DOS) that uses attention matrices to approximate inter-token dependencies.
result DOS consistently achieves superior performance on code generation and mathematical reasoning tasks.
Study shows attention-style models learn pairwise interactions efficiently.
problem Learning pairwise interactions in attention-style models.
method Proved minimax rate of convergence for learning pairwise interactions.
result Minimax rate is M−2β+12β independent of embedding dimension and token number. The paper explores how sinks and diagonal patterns prevent attention oversmoothing.
problem Preventing attention oversmoothing in neural networks.
method Analyzing geometric conditions and conditions for dense vs. sparse attention, proving equivalence between sinks and hard attention switch, and comparing the costs of sinks vs. diagonal patterns.
result Sinks and diagonal patterns effectively prevent attention oversmoothing, and diagonal patterns provide a more flexible approach.
Study predicts success of crypto-tokens on Pump.fun platform.
problem Identify factors affecting the success of new crypto-tokens.
method Build predictive models using bonding curve mechanism and structural/behavioral variables.
result Conditional variables significantly improve the predictive power of token success.
Self-attention networks localize when eigenspectrum variance is small.
problem Self-attention mechanisms can lead to rank and entropy collapses, reducing model expressivity and trainability.
method Characterized attention localization using query-key eigenspectrum variance.
result Small eigenspectrum variance prevents both rank and entropy collapses, improving model performance.