Study improves financial chatbot command understanding.
problem Improving chatbot command understanding for financial contexts.
method Sequence to sequence learning and Multi-Task Learning techniques.
result Enhanced performance in intent and content extraction.
Chatbot uses BERT to handle financial investment questions, improving accuracy and decision-making.
problem Improving accuracy and decision-making in financial investment customer service.
method Deep Bidirectional Transformer (BERT) model, uncertainty measure comparison, mixed-integer programming, automatic spelling correction.
result Chatbot can recognize 381 intents and decide when to escalate questions.
Self-feeding chatbots learn from user feedback to improve performance.
problem Lack of training data after deployment of dialogue agents.
method Extracts new training examples from user responses and uses feedback to improve dialogue abilities.
result Self-feeding chatbots significantly improve performance on PersonaChat dataset.
Topic-aware chatbot learns from NMF topic vectors.
problem Improving chatbot relevance based on user topics.
method Combines RNN with NMF for topic learning and attention.
result Chatbot provides more relevant answers based on topic.
Meena is a chatbot trained on social media data, achieving human-like conversation quality.
problem Creating a chatbot that can have human-like conversations in an open-domain setting.
method End-to-end training of a 2.6B parameter neural network on social media data, using perplexity and a human evaluation metric (SSA) to assess quality.
result Meena achieves a high human-like conversation quality (79% SSA) when compared to existing chatbots.
Hotel booking chatbot handles daily tens of thousands of searches.
problem Improving hotel booking through conversational AI.
method Frame-based dialogue management system with ML models for intent, entity recognition, and info retrieval.
result Chatbot deployed on a commercial scale, handling hotel searches daily.
Statistical framework improves LLM chatbot ranking.
problem Improving evaluation of LLM-based chatbots through pairwise comparisons.
method Factored tie model, covariance modeling, and parameter constraints.
result Substantial improvements in modeling pairwise comparison data.
Self-attentional models improve chatbot efficiency and performance.
problem Training efficient task-oriented dialogue generation systems.
method Applied self-attentional models to three datasets for chatbot training.
result Self-attentional models outperform recurrence-based models in efficiency and performance.
Information extraction and user intention identification are central topics in modern query understanding and recommendation systems. In this paper, we propose DeepProbe, a generic information-directed interaction framework which is built around an attention-based sequence to sequence (seq2seq) recurrent neural network…
We study reinforcement learning of chatbots with recurrent neural network architectures when the rewards are noisy and expensive to obtain. For instance, a chatbot used in automated customer service support can be scored by quality assurance agents, but this process can be expensive, time consuming and noisy. Previous …
Dropping a tiny fraction of preferences can significantly alter the rankings of top LLMs.
problem Robustness of LLM ranking systems to small changes in preference data.
method A computational method based on the Bradley-Terry model to evaluate robustness.
result Top LLM rankings can be highly sensitive to the removal of a small fraction of preferences.
Study uses chatbot to understand users' needs for ML model explanations.
problem Lack of understanding of user needs for model explanations.
method Developed a conversational system (dr_ant) to collect user questions about a machine learning model trained on Titanic data.
result Collected a corpus of 1000+ dialogues to identify common user questions.
Paper improves emotion expression in AI chatbots.
problem AI chatbots generate responses that lack emotion.
method Developed neural models to express specific emotions in generated responses.
result An encoder-decoder model with multiple attention layers performs best in expressing required emotion.
We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural langu…
We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural langu…
This paper tackles interpretability of LLMs in finance.
problem Complexity and lack of transparency of LLMs in finance.
method Mechanistic interpretability to understand LLM behavior.
result Demonstrates practical relevance of mechanistic interpretability in financial use cases.
AI helps simplify complex ship finance processes.
problem Complexity in ship finance due to data and regulatory requirements.
method Integrates large language models for document comprehension, information extraction, and workflow automation.
result AI-assisted systems can support maritime finance professionals in managing complex information and reporting requirements.
Unified framework to bridge human and LLM judgments.
problem Systematic discrepancies between human and LLM evaluations.
method Latent human preference score and linear transformations of covariates.
result Higher agreement with human ratings and exposure of systematic gaps.
Quriosity analyzes curiosity-driven questions from diverse sources.
problem Understanding and analyzing human curiosity-driven questions.
method Collection of 13.5K questions from various sources, development of an iterative prompt improvement framework.
result 42% of questions are causal, revealing unique linguistic properties.
Low-rank framework for task-specific LLM ranking from sparse comparisons.
problem Challenges in reliable task-specific ranking of LLMs under sparse, imbalanced comparisons.
method Low-rank modeling of task-by-model ability matrix, max-norm accurate estimator, task-wise top-K recovery guarantees, uncertainty quantification framework.
result Improves sample efficiency and produces tighter, better-calibrated ranking certificates.
Paper uses PPO and PPO-dynamic for sequence generation tasks, improving stability and performance.
problem Intractable backpropagation issue in sequence generation tasks.
method Replaces policy gradient with PPO and proposes a dynamic approach for PPO (PPO-dynamic).
result PPO and PPO-dynamic outperform policy gradient in sequence generation tasks.
The study analyzes the convergence rate of a large transformer model.
problem Understanding the convergence rate of over-parameterized transformer models.
method Theoretical analysis focusing on gradient descent optimization.
result Theoretical upper bound on missclassification probability.
CJE calibrates cheap LLM judges against an oracle, achieving high accuracy at a fraction of the cost.
problem Inexpensive LLM judges can produce biased rankings, leading to unreliable outcomes.
method CJE uses a small oracle to calibrate cheap scores, then evaluates at scale with valid uncertainty.
result CJE achieves 99% pairwise ranking accuracy at 14x lower cost compared to a 16x oracle/judge cost ratio.
Improved NER performance on imbalanced data.
problem Highly unbalanced training data in NER tasks.
method Adapted a neural architecture with CRF and BI-LSTM layers, using pre-trained embeddings. Introduced a two-class split to optimize performance.
result Significant improvement in performance for weak classes with minimal training data.
Proposes an iterative algorithm for optimizing attention mechanisms in large language models.
problem Optimizing attention mechanisms in large language models.
method Iterative algorithm for rescaled hyperbolic functions regression.
result Efficiency and generalizability of the rescaled softmax regression framework.
We provide an online RLHF workflow for large language models.
problem Lack of online RLHF workflow for large language models.
method Construct preference models using open-source datasets, approximate human feedback, and implement online iterative RLHF.
result Our LLM achieves state-of-the-art performance on various benchmarks.
A simple method reduces bias in LLM auto-evaluators by controlling output length.
problem Bias in LLM auto-annotators, particularly length bias.
method Simple regression analysis to control for length difference and other mediators.
result Improved robustness and increased correlation with human preferences.
Algorithm reduces audit costs by identifying best service configurations from biased textual evidence.
problem Designing service systems from textual evidence requires accurate selection despite biased automated scoring.
method Developed PP-LUCB algorithm combining LLM scores and selective audits to minimize costs.
result Correctly identified the best model in 40/40 trials with 90% cost reduction.
Study examines financial structure's impact on non-financial firms' growth in Kenya.
problem Declining financial performance and growth of non-financial firms listed at Nairobi Securities Exchange.
method Analyzes the effect of financial structure on financial growth.
result Established the impact of financial structure on non-financial firms' growth.
Study shows financial literacy, social capital, and financial tech positively impact financial inclusion of Indonesian students.
problem Financial literacy, social capital, and financial technology's impact on financial inclusion of Indonesian students.
method Quantitative research using questionnaires distributed to 100 students from 7 private colleges in Tangerang, Indonesia.
result Financial literacy, social capital, and financial technology have a positive and significant influence on financial inclusion.
New method accounts for hidden context in preference learning for RLHF models.
problem Incomplete data with hidden context affects RLHF model outcomes.
method Distributional Preference Learning (DPL) methods estimate hidden context distributions.
result DPL methods reduce RLHF vulnerabilities by accounting for hidden context.
New DL approach reveals feature construction in dense samples.
problem Understanding deep learning's effectiveness across diverse applications.
method High-density sample task with 5 unique tokens, 500 exemplars per token.
result Emergence of category structure and feature detectors observed.
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.
Financial planners helped preserve and increase household net financial assets during the Great Recession.
problem Impact of financial planners on household net financial assets during the Great Recession.
method Utilized 2007-2009 Survey of Consumer Finances (SCF) panel dataset, analyzed 3,862 respondents.
result Starting to use a financial planner during the Great Recession had a positive impact on preserving and increasing household net financial assets.
Motivated by recent financial crises significant research efforts have been put into studying contagion effects and herding behaviour in financial markets. Much less has been said about influence of financial news on financial markets. We propose a novel measure of collective behaviour in financial news on the Web, New…
Study human-machine interaction with private info using offline RL.
problem Confounding bias and distributional mismatch in offline RL for human-guided interaction.
method Developed a novel identification result and OPE method to address confounding bias, and used pessimism to tackle distributional mismatch.
result Policy pair converges to optimal one at satisfactory rate under mild assumptions.
Proposes LSTM for financial market trend forecasting.
problem Challenges in financial market trend forecasting.
method Uses LSTM for financial market trend forecasting.
result Improves performance compared to traditional methods.
Financial system being the place of metting capital flows (equality between saving and investment), a volatility of capital flows can destroy the robustness and good working of financial system, it means subvert financial stability. The same a weak financial system, few regulated and bad manage can exacerbate volatilit…
Model shows financial turbulence similar to turbulence, with wealth cascading from large to small entities.
problem Understanding wealth distribution and dynamics in financial systems.
method Constructed a multiscale model for hierarchical financial structures.
result Found wealth distribution exhibits power law at large scales and Maxwellian at small scales.
We consider dynamics of financial markets as dynamics of expectations and discuss such a dynamics from the point of view of phenomenological thermodynamics. We describe a financial Carnot cycle and the financial analogue of a heat machine. We see, that while in physics a perpetuum mobile is absolutely impossible, in ec…
This study presents an ANWSER model (asset network systemic risk model) to quantify the risk of financial contagion which manifests itself in a financial crisis. The transmission of financial distress is governed by a heterogeneous bank credit network and an investment portfolio of banks. Bankruptcy reproductive ratio …
Model financial time series with MOGP for imputation and prediction.
problem Impute missing financial data due to dependencies among multiple series.
method Use a multi-output Gaussian process (MOGP) with expressive covariance functions.
result The model outperforms other MOGPs and independent Gaussian process on real financial data.
Quantum computing aids in predicting financial crashes.
problem Predicting financial crashes when markets are disrupted.
method Mapped financial network to quantum Hamiltonian, solved using quantum annealing.
result Quantum computing can efficiently assess financial equilibrium and predict crashes.
Paper aims to use AI for detecting financial crimes, focusing on money laundering.
problem Financial institutions need better technologies to detect and predict financial crimes.
method Study recent works, develop a novel model for money laundering detection.
result Demonstrates a model for detecting money laundering cases with minimal human intervention.
Financial networks reveal systemic risk, suggesting new regulatory strategies.
problem Global financial interconnectedness and inadequacy of traditional risk models.
method Network-based models of financial systems to understand contagion and risk.
result Financial networks exhibit 'robust-yet-fragile' properties, informing cost-effective regulation.
UniFinEval benchmarks financial models across text, images, and videos.
problem Challenges in evaluating financial multimodal models across text, images, and videos.
method Proposes UniFinEval, a unified multimodal benchmark for financial scenarios.
result Gemini-3-pro-preview achieves best performance but still lags behind experts.
Paper assesses financial potential for enterprise development.
problem Determining financial potential for enterprise development.
method Stages of financial potential assessment based on literature analysis.
result Proposes a mechanism for managing enterprise financial potential.
FinBloom enhances LLMs for real-time financial queries.
problem Limited access to real-time financial data by LLMs.
method Developed a custom 7B parameter LLM, Financial Context Dataset, and a Financial Agent.
result Significantly improved LLMs' capability to handle dynamic financial tasks.