Related papers: Characterizing Model-Native Skills
Behavioral skills or policies for autonomous agents are conventionally learned from reward functions, via reinforcement learning, or from demonstrations, via imitation learning. However, both modes of task specification have their…
Many capable large language models (LLMs) are developed via self-supervised pre-training followed by a reinforcement-learning fine-tuning phase, often based on human or AI feedback. During this stage, models may be guided by their inductive…
Alignment training has tradeoffs: it helps language models (LMs) gain in reasoning and instruction following but might lose out on skills such as creativity and calibration, where unaligned base models are better at. We aim to make the best…
Large language models are increasingly used as computational tools for modeling human-like behavior. We introduce a behavioral induction framework that modifies model policies through fine-tuning on structured decision-making tasks: using…
As language models continue to scale in size and capability, they display an array of emerging behaviors, both beneficial and concerning. This heightens the need to control model behaviors. We hope to be able to control the personality…
Many methods now exist for conditioning model outputs on task instructions, retrieved documents, and user-provided explanations and feedback. Rather than relying solely on examples of task inputs and outputs, these approaches use valuable…
The named concepts and compositional operators present in natural language provide a rich source of information about the kinds of abstractions humans use to navigate the world. Can this linguistic background knowledge improve the…
Vision-Language-Action Models (VLAs) have shown remarkable progress towards embodied intelligence. While their architecture partially resembles that of Large Language Models (LLMs), VLAs exhibit higher complexity due to their multi-modal…
We advocate the development of a discipline of interacting with and extracting information from models, both mathematical (e.g. game-theoretic ones) and computational (e.g. agent-based models). We outline some directions for the development…
Structured latent attribute models (SLAMs) are a special family of discrete latent variable models widely used in social and biological sciences. This paper considers the problem of learning significant attribute patterns from a SLAM with…
Inference-time intervention (ITI) has emerged as a promising method for steering large language model (LLM) behavior in a particular direction (e.g., improving helpfulness) by intervening on token representations without costly updates to…
Agent skills, which are reusable, domain-specific knowledge artifacts, have become a popular mechanism for extending LLM-based agents, yet formally benchmarking skill usage performance remains scarce. Existing skill benchmarking efforts…
Language models have shown unprecedented capabilities, sparking debate over the source of their performance. Is it merely the outcome of learning syntactic patterns and surface level statistics, or do they extract semantics and a world…
Transformer language models have achieved state-of-the-art performance for a variety of natural language tasks but have been shown to encode unwanted biases. We evaluate the social biases encoded by transformers trained with the masked…
Recent work using auxiliary prediction task classifiers to investigate the properties of LSTM representations has begun to shed light on why pretrained representations, like ELMo (Peters et al., 2018) and CoVe (McCann et al., 2017), are so…
Human-like personality traits have recently been discovered in large language models, raising the hypothesis that their (known and as yet undiscovered) biases conform with human latent psychological constructs. While large conversational…
Transformer-based Large Language Models (LLMs) have revolutionized Natural Language Processing by demonstrating exceptional performance across diverse tasks. This study investigates the impact of the parameter initialization scale on the…
Large language models (LLMs) can sometimes report the strategies they actually use to solve tasks, yet at other times seem unable to recognize those strategies that govern their behavior. This suggests a limited degree of metacognition -…
Large language models can represent a variety of personas but typically default to a helpful Assistant identity cultivated during post-training. We investigate the structure of the space of model personas by extracting activation directions…
In this paper, we introduce Narrative Learning, a methodology where models are defined entirely in natural language and iteratively refine their classification criteria using explanatory prompts rather than traditional numerical…