Evil twins are not that evil: Qualitative insights into machine-generated prompts

It has been widely observed that language models (LMs) respond in predictable ways to algorithmically generated prompts that are seemingly unintelligible. This is both a sign that we lack a full understanding of how LMs work, and a practical challenge, because opaqueness can be exploited for harmful uses of LMs, such as jailbreaking. We present the first thorough analysis of opaque machine-generated prompts, or autoprompts, pertaining to 3 LMs of different sizes and families. We find that machine-generated prompts are characterized by a last token that is often intelligible and strongly affects the generation. A small but consistent proportion of the previous tokens are fillers that probably appear in the prompt as a by-product of the fact that the optimization process fixes the number of tokens. The remaining tokens tend to have at least a loose semantic relation with the generation, although they do not engage in well-formed syntactic relations with it. We find moreover that some of the ablations we applied to machine-generated prompts can also be applied to natural language sequences, leading to similar behavior, suggesting that autoprompts are a direct consequence of the way in which LMs process linguistic inputs in general.

Principles of semantic and functional efficiency in grammatical patterning

Grammatical features such as number and gender serve two central functions in human languages. While they encode salient semantic attributes like numerosity and animacy, they also offload sentence processing cost by predictably linking words together via grammatical agreement. Grammars exhibit consistent organizational patterns across diverse languages, invariably rooted in a semantic foundation, a widely confirmed but still theoretically unexplained phenomenon. To explain the basis of universal grammatical patterns, we unify two fundamental properties of grammar, semantic encoding and agreement-based predictability, into a single information-theoretic objective under cognitive constraints. Our analyses reveal that grammatical organization provably inherits from perceptual attributes, but that grammars empirically prioritize functional goals, promoting efficient language processing over semantic encoding.

Unnatural language processing: How do language models handle machine-generated prompts?

Language model prompt optimization research has shown that semantically and grammatically well-formed manually crafted prompts are routinely outperformed by automatically generated token sequences with no apparent meaning or syntactic structure, including sequences of vectors from a model's embedding space. We use machine-generated prompts to probe how models respond to input that is not composed of natural language expressions. We study the behavior of models of different sizes in multiple semantic tasks in response to both continuous and discrete machine-generated prompts, and compare it to the behavior in response to human-generated natural-language prompts. Even when producing a similar output, machine-generated and human prompts trigger different response patterns through the network processing pathways, including different perplexities, different attention and output entropy distributions, and different unit activation profiles. We provide preliminary insight into the nature of the units activated by different prompt types, suggesting that only natural language prompts recruit a genuinely linguistic circuit.

Cross-Domain Image Captioning with Discriminative Finetuning

Neural captioners are typically trained to mimic human-generated references without optimizing for any specific communication goal, leading to problems such as the generation of vague captions. In this paper, we show that fine-tuning an out-of-the-box neural captioner with a self-supervised discriminative communication objective helps to recover a plain, visually descriptive language that is more informative about image contents. Given a target image, the system must learn to produce a description that enables an out-of-the-box text-conditioned image retriever to identify such image among a set of candidates. We experiment with the popular ClipCap captioner, also replicating the main results with BLIP. In terms of similarity to ground-truth human descriptions, the captions emerging from discriminative finetuning lag slightly behind those generated by the non-finetuned model, when the latter is trained and tested on the same caption dataset. However, when the model is used without further tuning to generate captions for out-of-domain datasets, our discriminatively-finetuned captioner generates descriptions that resemble human references more than those produced by the same captioner without finetuning. We further show that, on the Conceptual Captions dataset, discriminatively finetuned captions are more helpful than either vanilla ClipCap captions or ground-truth captions for human annotators tasked with an image discrimination task.

Referential communication in heterogeneous communities of pre-trained visual deep networks

As large pre-trained image-processing neural networks are being embedded in autonomous agents such as self-driving cars or robots, the question arises of how such systems can communicate with each other about the surrounding world, despite their different architectures and training regimes. As a first step in this direction, we systematically explore the task of referential communication in a community of state-of-the-art pre-trained visual networks, showing that they can develop a shared protocol to refer to a target image among a set of candidates. Such shared protocol, induced in a self-supervised way, can to some extent be used to communicate about previously unseen object categories, as well as to make more granular distinctions compared to the categories taught to the original networks. Contradicting a common view in multi-agent emergent communication research, we find that imposing a discrete bottleneck on communication hampers the emergence of a general code. Moreover, we show that a new neural network can learn the shared protocol developed in a community with remarkable ease, and the process of integrating a new agent into a community more stably succeeds when the original community includes a larger set of heterogeneous networks. Finally, we illustrate the independent benefits of developing a shared communication layer by using it to directly transfer an object classifier from a network to another, and we qualitatively and quantitatively study its emergent properties.