Related papers: Conditional misalignment: common interventions can…

To help evaluate and understand the latent capabilities of language models, this paper introduces an approach using optimized input embeddings, or 'soft prompts,' as a metric of conditional distance between a model and a target behavior.…

In this paper we consider the problem of inference in statistical models characterized by moment restrictions by casting the problem within the Exponentially Tilted Empirical Likelihood (ETEL) framework. Because the ETEL function has a well…

While brain-aligned large language models (LLMs) have garnered attention for their potential as cognitive models and for potential for enhanced safety and trustworthiness in AI, the role of this brain alignment for linguistic competence…

Mixed linear regression is a well-studied problem in parametric statistics and machine learning. Given a set of samples, tuples of covariates and labels, the task of mixed linear regression is to find a small list of linear relationships…

Socio-economic causal effects depend heavily on their institutional and environmental contexts. The same intervention can produce different, even opposite, effects across regulatory regimes, market conditions, time periods, or populations.…

From the perspective of content safety issues, alignment has shown to limit large language models' (LLMs) harmful content generation. This intentional method of reinforcing models to not respond to certain user inputs seem to be present in…

Word embeddings are an essential component in a wide range of natural language processing applications. However, distributional semantic models are known to struggle when only a small number of context sentences are available. Several…

Diffusion models have emerged as powerful generative priors for high-dimensional inverse problems, yet learning them when only corrupted or noisy observations are available remains challenging. In this work, we propose a new method for…

Multi-level normal hierarchical models, also interpreted as mixed effects models, play an important role in developing statistical theory in multi-parameter estimation for a wide range of applications. In this article, we propose a novel…

Several phenomena are available representing market activity: volumes, number of trades, durations between trades or quotes, volatility - however measured - all share the feature to be represented as positive valued time series. When…

Language models have demonstrated remarkable performance in solving reasoning tasks; however, even the strongest models still occasionally make reasoning mistakes. Recently, there has been active research aimed at improving reasoning…

Alignment has quickly become a default ingredient in LLM development, with techniques such as reinforcement learning from human feedback making models act safely, follow instructions, and perform ever-better on complex tasks. While these…

Safety evaluation for advanced AI systems assumes that behavior observed under evaluation predicts behavior in deployment. This assumption weakens for agents with situational awareness, which may exploit regime leakage, cues distinguishing…

Without any explicit cross-lingual training data, multilingual language models can achieve cross-lingual transfer. One common way to improve this transfer is to perform realignment steps before fine-tuning, i.e., to train the model to build…

Shared mental models are critical to team success; however, in practice, team members may have misaligned models due to a variety of factors. In safety-critical domains (e.g., aviation, healthcare), lack of shared mental models can lead to…

The efficient exchange of information is an essential aspect of intelligent collective behavior. Event-triggered control and estimation achieve some efficiency by replacing continuous data exchange between agents with intermittent, or…

Large language models are being widely used across industries to generate content that contributes directly to key performance metrics, such as conversion rates. Pretrained models, however, often fall short when it comes to aligning with…

Large language models (LLMs) are increasingly used in decision-making contexts, but when they present answers without signaling low confidence, users may unknowingly act on erroneous outputs. Prior work shows that LLMs maintain internal…

Recent prompt-based approaches allow pretrained language models to achieve strong performances on few-shot finetuning by reformulating downstream tasks as a language modeling problem. In this work, we demonstrate that, despite its…

We study the problem of emergent communication, in which language arises because speakers and listeners must communicate information in order to solve tasks. In temporally extended reinforcement learning domains, it has proved hard to learn…