More Like this

1. Language Model Inversion

   Morris, John X; Zhao, Wenting; Chiu, Justin T; Shmatikov, Vitaly; Rush, Alexander M (May 2024, ICLR)

   Language models produce a distribution over the next token; can we use this information to recover the prompt tokens? We consider the problem of language model inversion and show that next-token probabilities contain a surprising amount of information about the preceding text. Often we can recover the text in cases where it is hidden from the user, motivating a method for recovering unknown prompts given only the model's current distribution output. We consider a variety of model access scenarios, and show how even without predictions for every token in the vocabulary we can recover the probability vector through search. On Llama-2 7b, our inversion method reconstructs prompts with a BLEU of 59 and token-level F1 of 78 and recovers 27% of prompts exactly. Code for reproducing all experiments is available at this http URL. 

   more » « less
2. Token Turing Machines are Efficient Vision Models

   https://doi.org/10.48550/arXiv.2409.07613  

   Jajal, Purvish; Eliopoulos, Nick John; Chou, Benjamin Shiue-Hal; Thiruvathukal, George K; Davis, James C; Lu, Yung-Hsiang (February 2025, The Computer Vision Foundation.)

   We propose Vision Token Turing Machines (ViTTM), an efficient, low-latency, memory-augmented Vision Transformer (ViT). Our approach builds on Neural Turing Machines and Token Turing Machines, which were applied to NLP and sequential visual understanding tasks. ViTTMs are designed for non-sequential computer vision tasks such as image classification and segmentation. Our model creates two sets of tokens: process tokens and memory tokens; process tokens pass through encoder blocks and read-write from memory tokens at each encoder block in the network, allowing them to store and retrieve information from memory. By ensuring that there are fewer process tokens than memory tokens, we are able to reduce the inference time of the network while maintaining its accuracy. On ImageNet-1K, the state-of-the-art ViT-B has median latency of 529.5ms and 81.0% accuracy, while our ViTTM-B is 56% faster (234.1ms), with 2.4 times fewer FLOPs, with an accuracy of 82.9%. On ADE20K semantic segmentation, ViT-B achieves 45.65mIoU at 13.8 frame-per-second (FPS) whereas our ViTTM-B model acheives a 45.17 mIoU with 26.8 FPS (+94%). 

   more » « less
3. Token Imbalance Adaptation for Radiology Report Generation

   Wu, Yuexin; Huang, I-Chan; Huang, Xiaolei (August 2023, Proceedings of Machine Learning Research)

   Mortazavi, Bobak J; Sarker, Tasmie; Beam, Andrew; Ho, Joyce C (Ed.)

   Imbalanced token distributions naturally exist in text documents, leading neural language models to overfit on frequent tokens. The token imbalance may dampen the robustness of radiology report generators, as complex medical terms appear less frequently but reflect more medical information. In this study, we demonstrate how current state-of-the-art models fail to generate infrequent tokens on two standard benchmark datasets (IU X-RAY and MIMIC-CXR) of radiology report generation. To solve the challenge, we propose the \textbf{T}oken \textbf{Im}balance Adapt\textbf{er} (\textit{TIMER}), aiming to improve generation robustness on infrequent tokens. The model automatically leverages token imbalance by an unlikelihood loss and dynamically optimizes generation processes to augment infrequent tokens. We compare our approach with multiple state-of-the-art methods on the two benchmarks. Experiments demonstrate the effectiveness of our approach in enhancing model robustness overall and infrequent tokens. Our ablation analysis shows that our reinforcement learning method has a major effect in adapting token imbalance for radiology report generation. 

   more » « less
4. LLMEffiChecker : Understanding and Testing Efficiency Degradation of Large Language Models

   https://doi.org/10.1145/3664812  

   Feng, Xiaoning; Han, Xiaohong; Chen, Simin; Yang, Wei (September 2024, ACM Transactions on Software Engineering and Methodology)

   Large Language Models (LLMs) have received much recent attention due to their human-level accuracy. While existing works mostly focus on either improving accuracy or testing accuracy robustness, the computation efficiency of LLMs, which is of paramount importance due to often vast generation demands and real-time requirements, has surprisingly received little attention. In this article, we make the first attempt to understand and test potential computation efficiency robustness in state-of-the-art LLMs. By analyzing the working mechanism and implementation of 20,543 public-accessible LLMs, we observe a fundamental property in LLMs that could be manipulated in an adversarial manner to reduce computation efficiency significantly. Our interesting observation is that the output length determines the computation efficiency of LLMs instead of the input, where the output length depends on two factors: an often sufficiently large yet pessimistic pre-configured threshold controlling the max number of iterations and a runtime-generated end of sentence (EOS) token. Our key motivation is to generate test inputs that could sufficiently delay the generation of EOS such that LLMs would have to go through enough iterations to satisfy the pre-configured threshold. We presentLLMEffiChecker, which can work under both white-box setting and black-box setting. In the white-box scenario,LLMEffiCheckerdevelops a gradient-guided technique that searches for a minimal and unnoticeable perturbation at character-level, token-level, and structure-level. In the black-box scenario,LLMEffiCheckeremploys a causal inference-based approach to find critical tokens and similarly applies three levels of imperceptible perturbation to them. Both the white-box and black-box settings effectively delay the appearance of EOS, compelling these inputs to reach the naturally unreachable threshold. To demonstrate the effectiveness ofLLMEffiChecker, we conduct a systematic evaluation on nine publicly available LLMs: Google T5, AllenAI WMT14, Helsinki-NLP translator, Facebook FairSeq, UNICAMP-DL translator, MarianMT, Google FLAN-T5, MBZUAI LaMini-GPT, and Salesforce CodeGen. Experimental results show thatLLMEffiCheckercan increase on average LLMs’ response latency and energy consumption by 325% to 3,244% and 344% to 3,616%, respectively, by perturbing just one character or token in the input sentence. Our case study shows that inputs generated byLLMEffiCheckersignificantly affect the battery power in real-world mobile devices (i.e., drain more than 30 times battery power than normal inputs). 

   more » « less
5. Parameter-Efficient Tuning with Special Token Adaptation

   Yang, Xiaocong Yang; Huang, James Y.; Zhou, Wenxuan; Chen, Muhao (May 2023, Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL))

   Vlachos, Andreas; Augenstein, Isabelle (Ed.)

   Parameter-efficient tuning aims at updating only a small subset of parameters when adapting a pretrained model to downstream tasks. In this work, we introduce PASTA, in which we only modify the special token representations (e.g., [SEP] and [CLS] in BERT) before the self-attention module at each layer in Transformer-based models. PASTA achieves comparable performance to fine-tuning in natural language understanding tasks including text classification and NER with up to only 0.029% of total parameters trained. Our work not only provides a simple yet effective way of parameter-efficient tuning, which has a wide range of practical applications when deploying finetuned models for multiple tasks, but also demonstrates the pivotal role of special tokens in pretrained language models. 

   more » « less