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.

169,291 papers · 148 categories

Trend · papers per month

6.3%12.5%18.8%25.0% · Mar 202019922001200920182026
48 results for human language processing

The paper fine-tunes language models using human preferences for natural language tasks.

problem Applying reinforcement learning to natural language tasks with human-defined rewards.
method Fine-tuning language models using reward learning techniques, leveraging generative pretraining.
result The approach achieves good results in natural language tasks like text continuation and summarization.

Bayesian EnKF improves sentence comprehension uncertainty modeling.

problem Uncertainty in human language comprehension, especially with ambiguous inputs.
method Bayesian framework using ensemble Kalman filter (EnKF) for uncertainty quantification.
result Enhanced model's ability to approximate human cognitive processing with linguistic ambiguities.

Study of sentence representations in AI shows parallels to human learning.

problem Understanding how AI systems learn and generalize from training data.
method Diagnostic tests, performance analysis, training distribution effects, representation changes with augmentations.
result AI systems can learn abstract rules and generalize under certain conditions, similar to human zero-shot reasoning.

Model predicts upcoming discourse referents using linguistic and script knowledge.

problem Predicting upcoming discourse referents based on linguistic knowledge.
method Built a computational model that predicts referents using linguistic knowledge and scripts.
result Script knowledge significantly improves model estimates of human predictions.

Paper presents a fast method to generate multimodal embeddings.

problem Integrating visual and linguistic information into a single representation.
method Learning a language-to-vision mapping to build multimodal embeddings.
result Mapped vectors outperform unimodal and multimodal baselines, especially in zero-shot settings.

Paper proposes RMFN for multimodal language analysis.

problem Modeling interactions between language, visual, and acoustic modalities.
method Recurrent Multistage Fusion Network (RMFN) decomposes fusion into stages focusing on subsets of multimodal signals.
result RMFN achieves state-of-the-art performance across multimodal sentiment analysis, emotion recognition, and speaker traits recognition datasets.

NLP techniques improve drug discovery by analyzing chemical and protein text.

problem Improving drug discovery through better analysis of chemical and protein text.
method Natural language processing techniques applied to biochemical entities.
result Enhanced prediction of molecular properties and design of novel molecules.

Paper trains models to resist spurious patterns by having humans revise documents.

problem Machine learning models often rely on spurious patterns, leading to poor performance.
method Humans revise documents to retain coherence and avoid unnecessary changes, creating a combined dataset.
result Models trained on combined datasets perform better than those trained on original or manipulated data alone.

A tutorial on neural machine translation and sequence-to-sequence models.

problem Handling human language through modeling sequential data.
method Explains and delves into neural networks and natural language processing techniques.
result Powerful tools for modeling sequential data in natural language.

This study applies neural models to automatically recognize medical entities from natural language.

problem Automated recognition of medical entities from natural language is complex and time-consuming.
method Utilizes deep neural sequence models trained on a large dataset of death certificates.
result Deep neural models can efficiently recognize medical entities from natural language.

Deep learning model separates syntax and semantics for better language generalization.

problem Standard deep learning methods struggle with systematic generalization in natural language.
method Implemented a Syntactic Attention model that separates syntactic and semantic processing.
result The Syntactic Attention model outperforms standard methods on a compositional generalization task.

Language-based methods improve human similarity approximations without requiring many human judgments.

problem Approximating human similarity judgments using pre-trained deep neural networks (DNNs) is challenging and expensive.
method Developed language-based methods to approximate human similarity judgments, validated with adaptive tag collection pipeline.
result Language-based methods significantly improve performance over DNN-based methods with fewer human judgments.

TRIBE model uses LLMs to simulate human trading behavior in bond markets.

problem Complexities in decentralized bond market transactions.
method Agent-based model augmented with LLMs to simulate human-like decision-making.
result Slight trade aversion in LLMs can lead to complete market collapse.

This paper refines human labeling as a measurement process, revealing four sources of variation.

problem Systematic variation in human labeling obscures model learning.
method Introduces a statistical framework to decompose labeling outcomes.
result Empirical evidence for four components of labeling variation.

Generative model learns motion to language and vice versa using deep RNNs.

problem Linking human motion and natural language for semantic representations and robot behaviors.
method Bidirectional mapping between motion and language using deep recurrent neural networks (RNNs) and sequence-to-sequence learning.
result Model generates realistic motions from natural language descriptions and vice versa.

XPO enhances RLHF by encouraging diverse responses, offering improved sample efficiency.

problem Limited exploration in RLHF leads to suboptimal models and bottlenecks.
method XPO is a simple one-line change to DPO, introducing a novel exploration bonus.
result XPO achieves strong theoretical guarantees and promising empirical performance.

Develops a statistical framework to measure uncertainty in model rankings based on human preferences.

problem Uncertainty in model rankings based on human preferences due to mismatch between human and model preferences.
method Statistical framework using pairwise comparisons by humans and models to provide rank-sets for each model.
result Rank-sets constructed using only pairwise comparisons by strong models often do not cover the true ranking of human preferences.

New RLHF approach mitigates bias in aligning LLMs with human preferences.

problem Algorithmic bias in RLHF leading to preference collapse.
method Preference Matching (PM) RLHF, using PM regularizer and conditional variant.
result 29% to 41% improvement in alignment with human preferences.

Study evaluates human vs. machine review generation, finds human assessments correlate better with lexical overlaps.

problem Evaluating natural language generation models for online reviews is challenging and inconsistent.
method Compared human evaluators with various automated evaluation methods, including discriminative and word overlap metrics.
result Human evaluators do not correlate well with discriminative evaluators, but correlate better with lexical overlaps.

This study uses computational methods to analyze Italo Calvino's 'Invisible Cities', improving on previous literary analysis.

problem Improving literary analysis through computational methods for a specific novel.
method Leveraging pretrained contextualized representations and unsupervised clustering methods to analyze the thematic groups of cities in Calvino's novel.
result The computational approach provides insights into the trustworthiness of Calvino's thematic categorization of cities.

Enhances drug discovery models by understanding human language.

problem Low predictive quality of activity prediction models in drug discovery.
method Proposes a novel architecture with separate chemical and natural language input modules and a contrastive pre-training objective.
result Improves predictive performance on few-shot and zero-shot learning benchmarks.

Existing language models such as n-grams for software code often fail to capture a long context where dependent code elements scatter far apart. In this paper, we propose a novel approach to build a language model for software code to address this particular issue. Our language model, partly inspired by human memory, i…

2016-08-09abs ↗pdf ↗

Paper evaluates word embedding techniques on Russian digital humanities datasets.

problem Evaluating word embedding techniques on Russian language datasets.
method Created and evaluated word intrusion and word analogy tasks on manually curated datasets.
result Baseline evaluations with word embedding models show differences in performance for Russian and English datasets.

Stable and consistent model alignment for language models without assuming human preference models.

problem Lack of statistical consistency in existing alignment methods.
method Relative density ratio optimization between preferred and mixture of preferred and non-preferred data distributions.
result Our approach achieves statistical consistency and stability, providing tighter convergence guarantees.

Large language models predict human sensory judgments across multiple modalities.

problem Determining the extent of perceptual information in language.
method State-of-the-art large language models were used to predict sensory judgments across six psychophysical datasets.
result Large language models can predict human sensory judgments across multiple modalities with significant correlation to human data.

Paper proposes a new RLHF framework for human preference learning.

problem Handling dependent online human preference outcomes with dynamic contexts.
method Two-stage algorithm with εε-greedy followed by exploitation; anti-concentration inequalities and matrix martingale concentration techniques.
result Our method achieves optimal regret bound and asymptotic normality of estimators.

LR-Robot automates SLRs with AI, expert oversight, and multidimensional analysis.

problem Efficient but contextually limited outputs from existing SLR frameworks.
method Human-in-the-loop process, structured knowledge sources, retrieval-augmented generation.
result Empirical demonstration of AI-driven literature synthesis in option pricing.

Efficiently identifies good policies by choosing contexts for human feedback.

problem Efficiently acquiring human feedback for preference alignment in large language models.
method Formalizes active exploration as a dueling bandit problem and proposes an active exploration algorithm with a polynomial worst-case regret bound.
result Proposed method outperforms baselines with limited human preferences on various language models and datasets.

Proposes RDASS for better Korean text summarization evaluation.

problem ROUGE scores fail to capture semantic meaning in Korean text summarization.
method Introduces RDASS metrics and a method to improve their correlation with human judgment.
result RDASS metrics correlate better with human judgment than ROUGE scores.

This paper reviews methods for interpreting deep learning models with sequential data.

problem Limited interpretability of deep learning models in sequential data domains.
method Reviews and compares techniques for sequential interpretability.
result Current techniques have limitations and future research is needed.

Direct Density Ratio Optimization aligns LLMs with human preferences without assuming specific models.

problem Statistical inconsistency in aligning LLMs with human preferences.
method Direct Density Ratio Optimization (DDRO) estimates density ratio directly.
result DDRO is statistically consistent, converging to true human preferences as data grows.