Research
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.

168,695 papers · 148 categories

Trend · papers per month

16324864 · May 202619922001200920172026
48 results for token-level entropy

Proposes integrating global and local entropy for more reliable LLMs.

problem Uncertainty in large language models (LLMs) leads to unreliable predictions.
method Measures global uncertainty from hidden-state matrices and local uncertainty from tokens, combining them via a multiplicative gate.
result Global-Local Uncertainty (GLU) outperforms unsupervised baselines across multiple models and benchmarks.

ECLIPSE detects AI hallucinations in finance with high accuracy.

problem Hallucinations in AI-generated answers limit safe deployment in finance.
method Combines entropy estimation and perplexity decomposition to measure model evidence use.
result ECLIPSE achieves ROC AUC of 0.89 and average precision of 0.90 on financial QA dataset.

Topic models are typically evaluated with respect to the global topic distributions that they generate, using metrics such as coherence, but without regard to local (token-level) topic assignments. Token-level assignments are important for downstream tasks such as classification. Even recent models, which aim to improv…

2019-05-18abs ↗pdf ↗

This research tackles uncertainty estimation in autoregressive structured prediction tasks.

problem Ensuring safety and robustness of AI systems through accurate uncertainty estimation.
method Develops a unified probabilistic ensemble-based framework for token-level and sequence-level uncertainty estimation.
result Provides baselines for error and out-of-domain detection on translation and speech recognition datasets.

The task of Natural Language Inference (NLI) is widely modeled as supervised sentence pair classification. While there has been a lot of work recently on generating explanations of the predictions of classifiers on a single piece of text, there have been no attempts to generate explanations of classifiers operating on …

2019-04-24abs ↗pdf ↗

Language models perform worse with implicit reward models than explicit ones.

problem Understanding why implicit reward models generalize worse than explicit ones.
method Investigated the root cause of the generalization gap between IM-RMs and EX-RMs.
result Implicit reward models rely more on superficial token-level cues, leading to worse generalization.

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.

Charmer improves character-level adversarial attacks for language models.

problem Efficiency and effectiveness of character-level adversarial attacks for language models.
method Query-based adversarial attack method that maintains semantic similarity.
result Charmer achieves high attack success rate and similar adversarial examples.

A new sampler for FLMs improves token-level decoding controls.

problem Sampling from FLMs using standard methods collapses marginals and produces invalid sequences.
method Samples clean one-hot endpoints from FLM token marginals and uses Ornstein-Uhlenbeck bridges conditioned on these endpoints.
result The method preserves token-wise posterior-predictive marginals and improves quality-diversity tradeoff.

New L2D framework allows deferring specific parts of a sequence prediction to experts.

problem Current L2D methods defer entire predictions, which is not ideal for long sequences.
method Proposes token-level and one-time rejectors to defer specific outputs of a model prediction to experts.
result Granular deferrals achieve better cost-accuracy tradeoffs than whole deferrals.

TROLL improves RL for LLMs by replacing clipping with a trust region projection.

problem Clipping in RL for LLMs causes instability and suboptimal performance.
method TROLL uses a discrete differentiable trust region projection to replace clipping, balancing computational cost and effectiveness.
result TROLL consistently outperforms PPO-like clipping in training speed, stability, and final success rates.

Efficiently estimates uncertainty for LLM-based entity linking in tabular data.

problem Accurate and reliable uncertainty estimates for LLM-based entity linking in tabular data.
method Self-supervised approach using token-level features for single-shot inference.
result Effective uncertainty estimates detected at a fraction of computational cost.

Language models allocate information storage, not collapsing into uniform representations.

problem Incomplete neural collapse in language model representations.
method Analyzing variance and information sharing across 14 models, proving an information floor.
result Within-class variance is allocated information storage, not collapsed into uniform representations.

This paper fine-tunes LLMs for stock return prediction using financial news.

problem Improving stock return forecasting accuracy using LLMs.
method Fine-tuning LLMs with text and forecasting modules, comparing encoder-only and decoder-only models, and integrating token-level representations.
result LLMs' aggregated token-level embeddings enhance return predictions for long-only and long-short portfolios.

This study explains RL training dynamics in LLMs, focusing on token-level optimization and reasoning pattern reshaping.

problem Understanding the training dynamics of RL in LLMs to improve their reasoning capabilities.
method Empirical analysis and theoretical modeling of RL training process, focusing on reasoning patterns and token optimization.
result RL primarily optimizes a sparse subset of critical tokens, reshaping reasoning pattern distributions and affecting model performance.

Power-SMC reduces inference latency for training-free LLM reasoning.

problem Training-free LLM reasoning with low latency.
method Power-SMC, a training-free Sequential Monte Carlo scheme targeting sequence-level power distribution.
result Power-SMC reduces inference latency from 16-28× to 1.4-3.3× over baseline decoding.

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.

Extends conformal prediction for controlling expected risk of monotone loss functions.

problem Controlling expected risk of monotone loss functions.
method Generalizes split conformal prediction with coverage guarantee, extending to distribution shift, quantile risk, multiple, adversarial, and expectations of U-statistics.
result Tight up to an O(1/n)\mathcal{O}(1/n) factor, with worked examples in computer vision and natural language processing.

InfoTree improves reinforcement learning by optimizing tool use with a greedy submodular approach.

problem Maximizing information from tool use in reinforcement learning with limited resources.
method Formalizes Rollout Informativeness, recasts state selection as submodular maximization, and uses UUCB and ABA.
result InfoTree outperforms existing methods across various benchmarks, improving performance by 18.2% on average.

Generating logical form equivalents of human language is a fresh way to employ neural architectures where long short-term memory effectively captures dependencies in both encoder and decoder units. The logical form of the sequence usually preserves information from the natural language side in the form of similar token…

2018-07-19abs ↗pdf ↗

Enhances RL by controlling policy stochasticity through trajectory entropy constraints.

problem Non-stationary Q-value estimation and short-sighted entropy tuning in maximum entropy RL.
method Proposes TECRL framework with separate Q-functions for reward and entropy, enforcing a trajectory entropy constraint.
result DSAC-E algorithm achieves higher returns and better stability on OpenAI Gym benchmarks.

Existing attention mechanisms are trained to attend to individual items in a collection (the memory) with a predefined, fixed granularity, e.g., a word token or an image grid. We propose area attention: a way to attend to areas in the memory, where each area contains a group of items that are structurally adjacent, e.g…

2018-10-23abs ↗pdf ↗

The paper calculates bounds for risk metrics and entropies under partial information constraints.

problem Analyzing risk metrics and entropies for unimodal, symmetric distributions with limited information.
method Develops lower and upper bounds for worst-case distortion riskmetrics and weighted entropy for unimodal, symmetric distributions with known mean and variance.
result Sharp upper bounds for distortion riskmetrics and weighted entropy for symmetric distributions.

The paper analyzes worst-case distortion risk metrics and weighted entropy under partial information.

problem Analyzing worst-case distortion risk metrics and weighted entropy with limited information.
method General distributions, partial information (mean and variance), various entropies and risk measures.
result Provides worst-case results for distortion risk metrics and weighted entropy.

HCLM framework uses entropy regularization for open learning systems.

problem Real-world AI challenges and limitations of deep learning.
method Dynamical and information-theoretic framework with entropy regularization.
result Geometric entropy surrogates, especially log-determinant covariance entropy, induce stronger and more stable information forces.

Framework controls uncertainty in LLMs without labels or probabilities.

problem Managing uncertainty in black-box LLMs without token-level probability or true labels.
method Integrates generative models, UCP, and conformal alignment to control uncertainty.
result Achieves close-to-nominal coverage and tighter thresholds than split UCP.

JES optimizes expensive functions by considering joint entropy over input and output spaces.

problem Optimizing expensive functions with limited evaluations.
method Joint Entropy Search (JES) considers joint entropy over input and output spaces.
result JES outperforms other information-theoretic methods in Bayesian optimization.

We give a notion of entropy for general gemetric structures, which generalizes well-known notions of topological entropy of vector fields and geometric entropy of foliations, and which can also be applied to singular objects, e.g. singular foliations, singular distributions, and Poisson structures. We show some basic p…

2011-09-24abs ↗pdf ↗

DAC enhances exploration in reinforcement learning with entropy regularization.

problem Improving exploration efficiency in reinforcement learning.
method Sample-aware entropy regularization using replay buffer action distributions.
result DAC significantly outperforms existing algorithms in reinforcement learning tasks.