Improved robot navigation using multi-head attention for natural language instructions.
problem Improving robot navigation in unfamiliar environments.
method Proposes a multi-head attention mechanism blending layer in a neural network model.
result Significant performance gains in translating instructions for unseen environments.
This paper proposes a new method to connect language and physical actions in reinforcement learning.
problem Connecting linguistic representations to the physical world in embodied agents.
method Language-conditioned goal generators to decouple sensorimotor learning from language acquisition.
result Agents can demonstrate a diversity of behaviors for any given instruction.
Valid certifies LLMs' domain adherence, bounding out-of-domain behavior.
problem Adversarial susceptibility of LLMs to generate out-of-domain outputs.
method VALID approach providing adversarial bounds as a certificate.
result Validates LLMs' domain adherence with meaningful certificates.
FLARKO uses LLMs, KGs, and KTO to generate profitable, behaviorally aligned financial recommendations.
problem Financial recommendation systems often fail to account for behavioral and regulatory factors.
method FLARKO integrates LLMs, KGs, and KTO to generate profitable and behaviorally aligned recommendations.
result FLARKO consistently outperforms state-of-the-art recommendation baselines on behavioral alignment and joint profitability.
New methods predict language model out-of-distribution behaviors using causal mechanisms.
problem Predicting how language models behave on unseen data.
method Two methods: counterfactual simulation and value probing.
result Both methods achieve high AUC-ROC and outperform causal-agnostic approaches in out-of-distribution settings.
New approach decouples skill learning and language grounding for autonomous agents.
problem Autonomous acquisition of skills without external instructions and feedback.
method Language-Goal-Behavior (LGB) architecture with semantic representation.
result Decouples skill learning and language grounding, enabling diversity and strategy switching.
ALMANACS benchmarks explainability methods on simulatability.
problem Evaluating the effectiveness of explainability methods for language models.
method ALMANACS is a simulatability benchmark that evaluates explainability methods on twelve safety-relevant topics.
result No explainability method outperforms the explanation-free control across all topics.
LLMs are compared to Markov chains for natural language processing.
problem Theoretical analysis of LLMs' generalization capabilities.
method Equivalence between LLMs and Markov chains, studying multi-step inference.
result Derives generalization bounds for LLMs, capturing their behavior in practice.
Researchers analyze the structure of token spaces in large language models.
problem Understanding the geometric and topological structure of token spaces in large language models.
method Developed estimators for the dimension and Ricci scalar curvature of the token subspace and applied them to three large language models.
result The token subspace is not a manifold but a stratified manifold with significantly negative Ricci curvature.
Modeling investor behavior from financial advisor notes using NLP.
problem Identifying behavioral coaching opportunities for financial advisors.
method Topic modeling and supervised classification model.
result Predicting investor needs during adverse market conditions.
Study reveals LLM personality patterns but lacks behavioral consistency.
problem Understanding and validating personality traits in LLMs.
method Characterized LLM personality across three dimensions: training dynamics, self-report validity, and intervention effects.
result Self-reported traits do not reliably predict behavior, and instructional alignment affects trait expression but not behavior.
Graph signal processing detects hallucinations in large language models.
problem Detecting factual reasoning from hallucinations in large language models.
method Modeling transformer layers as dynamic graphs, using spectral analysis to define diagnostics.
result Spectral signatures can distinguish different types of hallucinations and achieve high accuracy.
Study evaluates five LLMs for financial report analysis, revealing performance differences and variability.
problem Lack of understanding in reliability, consistency, and transparency of LLMs in financial analysis.
method Human evaluation, automated similarity metrics, and behavioral diagnostics applied to five transformer-based LLMs over U.S. 10-K filings.
result No single LLM consistently dominates across all evaluation perspectives, highlighting variability and need for interpretability.
FinHEAR combines LLMs with human expertise for better financial decision-making.
problem Challenges in financial decision-making for language models.
method Multi-agent framework with specialized LLMs for historical analysis, event interpretation, and expert retrieval.
result FinHEAR outperforms baselines in financial tasks with higher accuracy and risk-adjusted returns.
Humor is a unique and creative communicative behavior displayed during social interactions. It is produced in a multimodal manner, through the usage of words (text), gestures (vision) and prosodic cues (acoustic). Understanding humor from these three modalities falls within boundaries of multimodal language; a recent r…
New method evaluates AI stock prediction systems based on decision-making processes.
problem Lack of evaluation for AI systems' decision-making processes.
method Scores intermediate decision process using large language models and closed-loop reinforcement learning feedback.
result Composite behavioral score correlates with Sharpe ratio and reduces prediction error.
Describes explaining neurons in deep representations using compositional logical concepts.
problem Interpreting neuron behavior in deep neural networks.
method Identifying compositional logical concepts that closely approximate neuron behavior.
result Compositional explanations provide insights into model performance and allow for adversarial example creation.
Autonomous reinforcement learning agents, like children, do not have access to predefined goals and reward functions. They must discover potential goals, learn their own reward functions and engage in their own learning trajectory. Children, however, benefit from exposure to language, helping to organize and mediate th…
Linking human whole-body motion and natural language is of great interest for the generation of semantic representations of observed human behaviors as well as for the generation of robot behaviors based on natural language input. While there has been a large body of research in this area, most approaches that exist to…
We build deep RL agents that execute declarative programs expressed in formal language. The agents learn to ground the terms in this language in their environment, and can generalize their behavior at test time to execute new programs that refer to objects that were not referenced during training. The agents develop di…
This paper provides theoretical foundations for using quantized actions in behavior cloning.
problem Applying autoregressive models to continuous control requires discretizing actions through quantization, which is poorly understood.
method The paper analyzes quantization error propagation and statistical sample complexity, and proposes model-based augmentation.
result Behavior cloning with quantized actions achieves optimal sample complexity, matching existing lower bounds.
Triangulation filters spurious circuits in multilingual models.
problem Unreliable explanations of multilingual models across languages.
method Formalizes reference families and introduces triangulation as a causal acceptance rule.
result Triangulation provides a falsifiable standard for mechanistic claims.
StakeBench evaluates language understanding by linking comments to market commitments, improving model alignment with real-world outcomes.
problem Existing financial NLP benchmarks measure perceived language rather than market commitments.
method StakeBench uses observable market behavior to supervise models, testing their ability to detect commitments, identify sides, and project odds.
result Models partially recover position-side signals but struggle with later tasks, highlighting structural failures.
QuantAgent learns trading signals through self-improvement.
problem Building domain-specific knowledge for LLMs in quantitative investment.
method Two-layer loop approach: inner loop refines responses, outer loop tests and learns.
result QuantAgent approximates optimal trading behavior with provable efficiency.
Behavior cloning training instabilities amplified by SGD noise over long horizons.
problem Training instabilities in behavior cloning with deep neural networks.
method Empirical dissection of minibatch SGD updates and their effects on long-horizon rewards.
result Exponential moving average (EMA) of iterates effectively mitigates gradient variance amplification (GVA).
DLM-One speeds up language generation by 500x with continuous models.
problem Efficiently generating text sequences in natural language processing.
method Score-distillation of continuous diffusion language models.
result Achieves up to 500x speedup in inference time with competitive performance.
Study finds LLMs hallucinate in finance tasks, needing research.
problem Hallucination in LLMs in finance.
method Empirical investigation of four methods to mitigate hallucination.
result LLMs hallucinate in financial tasks.
StockAgent uses AI to simulate real-world stock trading, analyzing external factors and profitability.
problem Investors need to understand how external factors affect stock trading.
method Developed StockAgent, a multi-agent system driven by large language models.
result Identified how external factors impact trading behavior and profitability.
LLMs overestimate stock returns and are less accurate at predicting extreme outcomes.
problem Behavioral biases in LLMs' stock return forecasts.
method Comparison of LLM forecasts with crowd-sourced estimates and historical data.
result LLMs overestimate stock returns and are less accurate at predicting extreme outcomes.
Study examines bias in language models across multiple languages.
problem Assessing bias in language models across different languages.
method Semi-automatically translated data sets into multiple languages, analyzed mono- and multilingual models.
result Notable differences in bias across languages, with Turkish models showing least stereotypes.
In this work we present a technique to use natural language to help reinforcement learning generalize to unseen environments. This technique uses neural machine translation, specifically the use of encoder-decoder networks, to learn associations between natural language behavior descriptions and state-action informatio…
Pyro is a probabilistic programming language built on Python as a platform for developing advanced probabilistic models in AI research. To scale to large datasets and high-dimensional models, Pyro uses stochastic variational inference algorithms and probability distributions built on top of PyTorch, a modern GPU-accele…
BIG-bench benchmarks language models, revealing their strengths and weaknesses.
problem Understanding and quantifying the capabilities of large language models.
method Developed the BIG-bench benchmark with 204 tasks from various domains, evaluated across multiple model sizes and types.
result Model performance improves with scale but remains poor, with breakthrough behaviors often involving multiple steps.
Study evaluates if LLMs have company-specific biases in financial sentiment analysis.
problem Evaluating if large language models exhibit company-specific biases in financial sentiment analysis.
method Comparing sentiment scores with and without company names, constructing economic models, and empirical analysis.
result LLMs show company-specific biases in sentiment analysis, impacting investor behavior and stock prices.
This paper surveys imitation learning methods and challenges.
problem Difficulty in programming AI systems in complex environments.
method Learning from expert demonstrations to adapt behaviors.
result Overview of recent advances and emerging areas in IL.
ELS framework improves safety alignment by dynamically steering LLMs towards helpful responses.
problem Over-Refusal in Aligned Large Language Models
method Fine-tuning free framework using an Energy-Based Model (EBM) to dynamically steer LLMs during inference.
result Extensive experiments show a significant reduction in false refusals (from 57.3% to 82.6%) while maintaining safety performance.
New method uses low logit rank to simplify complex language models.
problem Understanding and learning from modern language models.
method Exploiting the low logit rank structure of language models for efficient learning.
result An efficient algorithm for learning low logit rank models from queries.
The goal of program synthesis is to automatically generate programs in a particular language from corresponding specifications, e.g. input-output behavior. Many current approaches achieve impressive results after training on randomly generated I/O examples in limited domain-specific languages (DSLs), as with string tra…
TRAK traces model predictions to training data efficiently.
problem Inefficiency in data attribution methods for large-scale models.
method TRAK: a new data attribution method that is both effective and computationally tractable.
result TRAK matches the performance of methods requiring thousands of models with just a handful.
We present an open-source tool for visualizing multi-head self-attention in Transformer-based language representation models. The tool extends earlier work by visualizing attention at three levels of granularity: the attention-head level, the model level, and the neuron level. We describe how each of these views can he…
AI agents in experimental markets exhibit behavioral patterns that aggregate into market dynamics.
problem Understanding AI trading behavior and its impact on market dynamics.
method Experimental asset markets populated by AI agents trained on Large Language Models (LLMs).
result AI agents' behavior leads to market dynamics similar to human traders, including bubbles.
This study examines how the size and alignment of pretraining data affect the performance of large language models on downstream tasks.
problem Understanding how the size and alignment of pretraining data impact the performance of large language models on downstream tasks.
method Investigated the scaling behavior of large language models in a transfer learning setting, focusing on machine translation tasks.
result The size of the finetuning dataset and the distribution alignment between pretraining and downstream data significantly influence the scaling behavior of downstream performance.
Characterizing temporal dependence patterns is a critical step in understanding the statistical properties of sequential data. Long Range Dependence (LRD) --- referring to long-range correlations decaying as a power law rather than exponentially w.r.t. distance --- demands a different set of tools for modeling the unde…
Adam outperforms gradient descent on language models due to handling heavy-tailed class imbalance.
problem Heavy-tailed class imbalance in language tasks.
method Comparing Adam and gradient descent on various architectures and data types, focusing on the impact of class imbalance.
result Class imbalance causes slow convergence for gradient descent, while Adam and sign-based methods are less affected.
LLMs prefer Bitcoin under crisis frames, affecting financial decisions.
problem Testing whether LLMs have built-in biases towards specific financial assets.
method Developed a three-level audit protocol to examine Bitcoin's representation and influence in LLMs.
result An identifiable internal feature in LLMs can be perturbed to move financial choices, but only within measurable limits.
Edge language models show bias over time, especially on resource-constrained devices.
problem Bias in edge language models on resource-constrained devices.
method Comparative analysis of text-based bias across edge, cloud, and desktop environments; optimized Llama-2 model on Raspberry Pi 4; feedback loop mechanism to correct bias.
result Llama-2 on Raspberry Pi 4 shows 43.23% and 21.89% more bias over time compared to cloud and desktop models.
Shapley values explain financial language models, aligning with domain knowledge.
problem Lack of explainability in financial applications of large language models.
method Shapley value analysis for financial textual data.
result Shapley values provide consistent explanations with financial reasoning.
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.