Large Language Models (LLMs) have an unrivaled and invaluable ability to "align" their output to a diverse range of human preferences, by mirroring them in the text they generate. The internal characteristics of such models, however, remain largely opaque. This work presents the Injectable Realignment Model (IRM) as a novel approach to language model interpretability and explainability. Inspired by earlier work on Neural Programming Interfaces, we construct and train a small network -- the IRM -- to induce emotion-based alignments within a 7B parameter LLM architecture. The IRM outputs are injected via layerwise addition at various points during the LLM's forward pass, thus modulating its behavior without changing the weights of the original model. This isolates the alignment behavior from the complex mechanisms of the transformer model. Analysis of the trained IRM's outputs reveals a curious pattern. Across more than 24 training runs and multiple alignment datasets, patterns of IRM activations align themselves in striations associated with a neuron's index within each transformer layer, rather than being associated with the layers themselves. Further, a single neuron index (1512) is strongly correlated with all tested alignments. This result, although initially counterintuitive, is directly attributable to design choices present within almost all commercially available transformer architectures, and highlights a potential weak point in Meta's pretrained Llama 2 models. It also demonstrates the value of the IRM architecture for language model analysis and interpretability. Our code and datasets are available at https://github.com/DRAGNLabs/injectable-alignment-model

Researchers often rely on humans to code (label, annotate, etc.) large sets of texts. This kind of human coding forms an important part of social science research, yet the coding process is both resource intensive and highly variable from application to application. In some cases, efforts to automate this process have achieved human-level accuracies, but to achieve this, these attempts frequently rely on thousands of hand-labeled training examples, which makes them inapplicable to small-scale research studies and costly for large ones. Recent advances in a specific kind of artificial intelligence tool - language models (LMs) - provide a solution to this problem. Work in computer science makes it clear that LMs are able to classify text, without the cost (in financial terms and human effort) of alternative methods. To demonstrate the possibilities of LMs in this area of political science, we use GPT-3, one of the most advanced LMs, as a synthetic coder and compare it to human coders. We find that GPT-3 can match the performance of typical human coders and offers benefits over other machine learning methods of coding text. We find this across a variety of domains using very different coding procedures. This provides exciting evidence that language models can serve as a critical advance in the coding of open-ended texts in a variety of applications.

It is notoriously difficult to control the behavior of artificial neural networks such as generative neural language models. We recast the problem of controlling natural language generation as that of learning to interface with a pretrained language model, just as Application Programming Interfaces (APIs) control the behavior of programs by altering hyperparameters. In this new paradigm, a specialized neural network (called a Neural Programming Interface or NPI) learns to interface with a pretrained language model by manipulating the hidden activations of the pretrained model to produce desired outputs. Importantly, no permanent changes are made to the weights of the original model, allowing us to re-purpose pretrained models for new tasks without overwriting any aspect of the language model. We also contribute a new data set construction algorithm and GAN-inspired loss function that allows us to train NPI models to control outputs of autoregressive transformers. In experiments against other state-of-the-art approaches, we demonstrate the efficacy of our methods using OpenAI's GPT-2 model, successfully controlling noun selection, topic aversion, offensive speech filtering, and other aspects of language while largely maintaining the controlled model's fluency under deterministic settings.

In the world of online gaming, not all actions are created equal. For example, when a player's character is confronted with a closed door, it would not make much sense to brandish a weapon, apply a healing potion, or attempt to barter. A more reasonable response would be to either open or unlock the door. The term interaction mode embodies the idea that many potential actions are neither useful nor applicable in a given situation. This paper presents a AEGIM, an algorithm for the automated extraction of game interaction modes via a semantic embedding space. AEGIM uses an image captioning system in conjunction with a semantic vector space model to create a gestalt representation of in-game screenshots, thus enabling it to detect the interaction mode evoked by the game.

Autonomous agents must often detect affordances: the set of behaviors enabled by a situation. Affordance detection is particularly helpful in domains with large action spaces, allowing the agent to prune its search space by avoiding futile behaviors. This paper presents a method for affordance extraction via word embeddings trained on a Wikipedia corpus. The resulting word vectors are treated as a common knowledge database which can be queried using linear algebra. We apply this method to a reinforcement learning agent in a text-only environment and show that affordance-based action selection improves performance most of the time. Our method increases the computational complexity of each learning step but significantly reduces the total number of steps needed. In addition, the agent's action selections begin to resemble those a human would choose.