In particular, V oicebox outperforms the state-of-the-art zero-shot TTS model V ALL-E on both intelligibility (5.9% vs 1.9% word error rates) and audio similarity (0.580 vs 0.681) while being up to 20 times faster.

This paper proposes a novel semiotic framework for analyzing Large Language Models (LLMs), conceptualizing them as stochastic semiotic engines whose outputs demand active, asymmetric human interpretation. We formalize the trade-off between expressive richness (semiotic breadth) and interpretive stability (decipherability) using information-theoretic tools. Breadth is quantified as source entropy, and decipherability as the mutual information between messages and human interpretations. We introduce a generative complexity parameter (lambda) that governs this trade-off, as both breadth and decipherability are functions of lambda. The core trade-off is modeled as an emergent property of their distinct responses to $λ$. We define a semiotic channel, parameterized by audience and context, and posit a capacity constraint on meaning transmission, operationally defined as the maximum decipherability by optimizing lambda. This reframing shifts analysis from opaque model internals to observable textual artifacts, enabling empirical measurement of breadth and decipherability. We demonstrate the framework's utility across four key applications: (i) model profiling; (ii) optimizing prompt/context design; (iii) risk analysis based on ambiguity; and (iv) adaptive semiotic systems. We conclude that this capacity-based semiotic approach offers a rigorous, actionable toolkit for understanding, evaluating, and designing LLM-mediated communication.

Vision-Language Models seamlessly discriminate among arbitrary semantic categories, yet they still suffer from poor generalization when presented with challenging examples.

We propose using mechanistic interpretability – techniques for reverse engineering model weights into human-interpretable algorithms – to derive and compactly prove formal guarantees on model performance. We prototype this approach by formally proving accuracy lower bounds for a small transformer trained on Max-of-K, validating proof transferability across 151 random seeds and four values of K. We create 102 different computer-assisted proof strategies and assess their length and tightness of bound on each of our models. Using quantitative metrics, we find that shorter proofs seem to require and provide more mechanistic understanding. Moreover, we find that more faithful mechanistic understanding leads to tighter performance bounds. We confirm these connections by qualitatively examining a subset of our proofs. Finally, we identify compounding structureless errors as a key challenge for using mechanistic interpretability to generate compact proofs on model performance.

All experiments were conducted on a single NVIDIA RTX 3090 GPU. The obtained text features were also projected into the CLIP latent space via an FC layer. The test images followed the same process except that the center cropping was used. Besides, the classification accuracy is adopted for Adience. Image Aesthetics Assessment An ImageNet pre-trained VGG-16 was used as the image encoder.

Below is the implementation of stochastic adjoint method with torch.autograd.Function in PyTorch. The roles of most helper functions and variables can be informed from their names and comments.

In particular, V oicebox outperforms the state-of-the-art zero-shot TTS model V ALL-E on both intelligibility (5.9% vs 1.9% word error rates) and audio similarity (0.580 vs 0.681) while being up to 20 times faster.

Vision-Language Models seamlessly discriminate among arbitrary semantic categories, yet they still suffer from poor generalization when presented with challenging examples.

We propose using mechanistic interpretability – techniques for reverse engineering model weights into human-interpretable algorithms – to derive and compactly prove formal guarantees on model performance. We prototype this approach by formally proving accuracy lower bounds for a small transformer trained on Max-of-K, validating proof transferability across 151 random seeds and four values of K. We create 102 different computer-assisted proof strategies and assess their length and tightness of bound on each of our models. Using quantitative metrics, we find that shorter proofs seem to require and provide more mechanistic understanding. Moreover, we find that more faithful mechanistic understanding leads to tighter performance bounds. We confirm these connections by qualitatively examining a subset of our proofs. Finally, we identify compounding structureless errors as a key challenge for using mechanistic interpretability to generate compact proofs on model performance.

Large Language Models (LLMs) have recently been applied to reranking tasks in information retrieval, achieving strong performance. However, their high computational demands often hinder practical deployment. Existing studies evaluate the efficiency of LLM-based rerankers using proxy metrics such as latency, the number of forward passes, input tokens, and output tokens. However, these metrics depend on hardware and running-time choices (\eg parallel or not, batch size, etc), and often fail to account for model size, making it difficult to interpret and obscuring the evaluation of the efficiency-effectiveness tradeoff. To address this issue, we propose \ours\footnote{https://github.com/zhiyuanpeng/EER-FLOPs.} for LLM-based rerankers: RPP (ranking metrics per PetaFLOP), measuring how much ranking quality (e.g., NDCG or MRR) a method achieves per PetaFLOP, and QPP (queries per PetaFLOP), measuring how many queries can be processed per PetaFLOP. Accompanied by the new metrics, an interpretable FLOPs estimator is developed to estimate the FLOPs of an LLM-based reranker even without running any experiments. Based on the proposed metrics, we conduct comprehensive experiments to evaluate a wide range of LLM-based rerankers with different architectures, studying the efficiency-effectiveness trade-off and bringing this issue to the attention of the research community.