Entity-GCN model answers multi-document questions by reasoning across documents.
problem Answering questions based on multiple documents and cross-document relations.
method Graph Convolutional Networks (GCNs) applied to a graph of mentions and their relations.
result Achieves state-of-the-art results on WikiHop dataset.
FinReflectKG benchmarks financial QA by linking relevant context from a financial KG, improving model performance and efficiency.
problem Efficiently retrieving and navigating relevant financial information across diverse sources and years.
method A benchmark built on a temporally indexed financial KG, generating QA pairs via pattern-specific prompts and quality control, evaluating retrieval scenarios.
result KG-guided retrieval yields substantial gains in correctness and token utilization, improving model performance by 24%.
Extract fairness policies from legal documents using machine learning.
problem Extract fairness policies from legal documents for AI applications.
method Two approaches based on semantic relatedness: Wordnet-based similarity and vector-based similarity.
result Vector-based similarity outperforms classical Wordnet-based similarity.
A CBR system investigates the TS-SS metric for document similarity.
problem Finding the most similar documents for user queries.
method Case-Based Reasoning (CBR) with TS-SS, Euclidean, and Cosine similarity measures.
result TS-SS metric shows surprising inappropriateness for high-dimensional features.
Clinical notes are text documents that are created by clinicians for each patient encounter. They are typically accompanied by medical codes, which describe the diagnosis and treatment. Annotating these codes is labor intensive and error prone; furthermore, the connection between the codes and the text is not annotated…
We introduce a novel latent grouping model for predicting the relevance of a new document to a user. The model assumes a latent group structure for both users and documents. We compared the model against a state-of-the-art method, the User Rating Profile model, where only users have a latent group structure. We estimat…
INFUSER improves reasoning by self-evolving with a generator and solver that co-learn from unstructured documents.
problem Improving reasoning through self-evolution
method INFUSER uses a generator and solver co-evolving in a document pool to improve reasoning.
result INFUSER outperforms strong self-evolution baselines on Olympiad and SuperGPQA benchmarks.
Study shows GPT's earnings forecasts are human-like but not always accurate.
problem Information friction in AI-generated financial analysis.
method Examined GPT's earnings forecasts following corporate earnings releases and proposed a diagnostic framework.
result GPT's narrative attention is consistent and human-like but not always associated with higher forecast accuracy.
CCAligned creates a massive web document dataset for cross-lingual research.
problem Identifying comparable documents across different languages.
method Using URL signals to label web documents and mining Common Crawl corpus.
result Release of a dataset with over 392 million URL pairs from 8144 language pairs.
FAKTA automates fact checking across media sources.
problem Automating fact checking across diverse media sources.
method Unified framework integrating document retrieval, stance detection, evidence extraction, and linguistic analysis.
result FAKTA predicts factuality and provides evidence for claims.
Investors can enhance their portfolios by strategically using LETFs, especially with dynamic strategies.
problem Unsuitability of passive or static approaches to LETFs leads to undesirable risk-return profiles.
method Demonstrated the effectiveness of simple dynamic strategies in exploiting favorable Omega ratio dynamics.
result Dynamic strategies can exploit the compounding effect of LETFs, improving risk-return profiles.
A new method learns term weights for better text classification.
problem Improving text classification performance using term weighting.
method Learning to Weight (LTW) approach that optimizes term weights on training data.
result Learning to Weight (LTW) outperforms previous term weighting approaches in text classification.
SemSentSum uses embeddings to link facts across documents efficiently.
problem Linking facts across documents is challenging due to language variability.
method Develops SemSentSum, a fully data-driven model using universal and domain-specific sentence embeddings to build a semantic relation graph.
result SemSentSum achieves competitive results on multi-document summarization tasks.
Word embedding maps words into a low-dimensional continuous embedding space by exploiting the local word collocation patterns in a small context window. On the other hand, topic modeling maps documents onto a low-dimensional topic space, by utilizing the global word collocation patterns in the same document. These two …
Document clustering and topic modeling are two closely related tasks which can mutually benefit each other. Topic modeling can project documents into a topic space which facilitates effective document clustering. Cluster labels discovered by document clustering can be incorporated into topic models to extract local top…
Paper develops a new unsupervised scoring function for cross-lingual document alignment.
problem Aligning documents across different languages for NLP tasks.
method Uses cross-lingual sentence embeddings to compute semantic distances and guides document alignment.
result The proposed scoring function outperforms current methods by 7-22% on various language pairs.
FinCausal 2020 task detects financial document causality.
problem Detect causal relationships in financial documents.
method Binary classification and relation extraction tasks.
result 16 teams participated, 13 submitted system descriptions.
We develop the multilingual topic model for unaligned text (MuTo), a probabilistic model of text that is designed to analyze corpora composed of documents in two languages. From these documents, MuTo uses stochastic EM to simultaneously discover both a matching between the languages and multilingual latent topics. We d…
Trade-R1 bridges verifiable rewards to stochastic financial markets via process-level reasoning verification.
problem Extending RL to financial markets where rewards are verifiable but noisy.
method A verification method that transforms reasoning over financial documents into a structured RAG task, using a triangular consistency metric.
result DSR achieves superior cross-market generalization while maintaining reasoning consistency.
ABOUT ML aims to improve transparency in ML lifecycle documentation.
problem Lack of standard documentation in machine learning lifecycle.
method Initiative to operationalize ML transparency and standardize documentation.
result Helps address gaps in ML lifecycle documentation.
INFUSER improves reasoning by co-evolving a generator and solver with adaptive curriculum.
problem Improving reasoning in language models with minimal external supervision.
method INFUSER uses a Generator and Solver to co-evolve iteratively, rewarding the Generator with an influence score and the Solver with correctness rewards.
result INFUSER outperforms self-evolution baselines by over 20% on Olympiad and SuperGPQA benchmarks.
Transformers with CoT don't enhance reasoning power across all tasks.
problem Does CoT enhance the reasoning power of transformers?
method Examined the memorization capabilities of fixed-precision transformers with and without CoT.
result Transformers with CoT cannot memorize all reasoning tasks, leading to a negative answer.
Classic Topic Models are built under the Bag Of Words assumption, in which word position is ignored for simplicity. Besides, symmetric priors are typically used in most applications. In order to easily learn topics with different properties among the same corpus, we propose a new line of work in which the paragraph str…
Topic models have proven to be a useful tool for discovering latent structures in document collections. However, most document collections often come as temporal streams and thus several aspects of the latent structure such as the number of topics, the topics' distribution and popularity are time-evolving. Several mode…
Framework tracks evolving news stories across multiple sources.
problem Tracking evolving news stories across diverse sources and formats.
method Cross-domain story tracking approach using entity graphs and learning-to-rank.
result Outperforms state-of-the-art methods for real-time story tracking.
HC test measures word-frequency similarity for authorship attribution.
problem Identifying the author of a document based on word-frequency patterns.
method Adapting Higher Criticism (HC) to compare word-frequency tables.
result HC identifies characteristic words of the author, unaffected by topic structure.
In text mining, information retrieval, and machine learning, text documents are commonly represented through variants of sparse Bag of Words (sBoW) vectors (e.g. TF-IDF). Although simple and intuitive, sBoW style representations suffer from their inherent over-sparsity and fail to capture word-level synonymy and polyse…
Study compares methods for improving document retrieval accuracy.
problem Improving document retrieval accuracy from large corpora.
method Comparison of query expansion, topic models, and active learning.
result Active learning outperforms keyword lists in most settings.
Develops a flexible deep autoencoding topic model with scalable hybrid Bayesian inference.
problem Flexible and interpretable document analysis models.
method DATM with hybrid Bayesian inference, including topic-layer-adaptive stochastic gradient Riemannian MCMC and Weibull variational encoder.
result Demonstrates scalability and efficacy on big corpora in unsupervised and supervised learning tasks.
MARGE learns to reconstruct text by paraphrasing, achieving strong performance across multiple tasks.
problem Training sequence-to-sequence models with limited supervision.
method Unsupervised multi-lingual multi-document paraphrasing objective.
result Strong zero-shot performance on document translation and various tasks in multiple languages.
SAE-FiRE extracts key financial info from long documents, improving earnings surprise predictions.
problem Predicting earnings surprises from long, redundant financial documents.
method Sparse Autoencoder feature selection to filter out noise and identify key dimensions.
result SAE-FiRE significantly outperforms baseline approaches in financial datasets.
LLMs help automate extraction of actuarial variables from unstructured claims data.
problem Manual processing of unstructured claims data is time-consuming and inconsistent.
method Two-stage processing architecture using LLMs, modular Python pipeline.
result LLM-based extraction achieved high accuracy and practical actuarial value.
A new test assesses text similarity between two groups of documents.
problem Comparing similarity between two groups of documents.
method Neural network-based language models estimate entropy, and a test statistic derived from an estimation-and-inference framework is used.
result The proposed test maintains the nominal Type one error rate while offering greater power compared to existing methods.
The joint PLDA model, is a generalization of PLDA where the nuisance variable is no longer considered independent across samples, but potentially shared (tied) across samples that correspond to the same nuisance condition. The original work considered a single nuisance condition, deriving the EM and scoring formulas fo…
Method quantifies sentiment across languages without labeled data.
problem Performing sentiment analysis across multiple languages without labeled data.
method Combining quantification methods with cross-lingual vectorial representations.
result Cross-lingual sentiment quantification achieved surprising accuracy.
Proposes new methods for interpreting document classification models.
problem Interpretation fragility of attention-based neural networks.
method Corpus-level and concept-based explanation methods using attention weights.
result Extracts semantically meaningful keywords and concepts for model predictions.
Improves text clustering by incorporating sequential features and word embeddings.
problem Lack of sequential information and synonym handling in current text clustering methods.
method SiDPMM model that models documents as joint of bags of words, sequential features, and word embeddings.
result Significant improvement in performance and accurate inference of cluster numbers.
Proposes CLRS-Text, a new benchmark for evaluating LM reasoning capabilities.
problem Lack of transferable benchmarks for evaluating reasoning capabilities of language models.
method Developed a textual version of the CLRS benchmark, generating diverse algorithmic tasks.
result Demonstrates a novel challenge for the LM reasoning community and validates prior work.
ORCA calibrates LLMs for efficient, generalizable reasoning.
problem Miscalibration of large language models leading to inefficiencies.
method Online Reasoning Calibration (ORCA) using conformal prediction and test-time training.
result ORCA provides higher efficiency and generalization across different reasoning tasks.
Finding relevant information from large document collections such as the World Wide Web is a common task in our daily lives. Estimation of a user's interest or search intention is necessary to recommend and retrieve relevant information from these collections. We introduce a brain-information interface used for recomme…
An ongoing challenge in the analysis of document collections is how to summarize content in terms of a set of inferred themes that can be interpreted substantively in terms of topics. The current practice of parametrizing the themes in terms of most frequent words limits interpretability by ignoring the differential us…
TRR detects stock portfolio crashes by simulating human reasoning.
problem Detecting stock portfolio crashes with limited historical data.
method Temporal Relational Reasoning (TRR) framework.
result TRR outperforms state-of-the-art techniques in detecting stock portfolio crashes.
Develops deep NMF models using β-divergences for feature extraction.
problem Inadequate evaluation metrics for deep NMF on diverse datasets.
method Introduces new deep NMF models using Kullback-Leibler divergence.
result Improves feature extraction quality across different types of data.
We present a novel hierarchical distance-dependent Bayesian model for event coreference resolution. While existing generative models for event coreference resolution are completely unsupervised, our model allows for the incorporation of pairwise distances between event mentions -- information that is widely used in sup…
In dynamic topic modeling, the proportional contribution of a topic to a document depends on the temporal dynamics of that topic's overall prevalence in the corpus. We extend the Dynamic Topic Model of Blei and Lafferty (2006) by explicitly modeling document level topic proportions with covariates and dynamic structure…
Unified model learns concepts across domains like left and right.
problem Limited generalization of language concepts in inference-only models.
method Logic-Enhanced Foundation Model (LEFT) with a differentiable, domain-independent program executor.
result LEFT flexibly learns and reasons with concepts across 2D images, 3D scenes, human motions, and robotic manipulation.
This paper improves topic model estimation for sparse distributions and applies it to Wasserstein distances.
problem Estimating sparse topic distributions in topic models with high-dimensional data.
method MLE for topic weights when A is known, plug-in estimator for unknown A. result MLE can be exactly sparse and contain true zero pattern of topic weights.
VERAFI improves financial AI by verifying calculations and compliance.
problem Financial AI systems generate errors and violations during reasoning.
method VERAFI combines dense retrieval, reranking, and automated reasoning policies.
result VERAFI achieves 94.7% factual correctness, 81% relative improvement.