With the increasing prevalence of text generated by large language models (LLMs), there is a growing concern about distinguishing between LLM-generated and human-written texts in order to prevent the misuse of LLMs, such as the dissemination of misleading information and academic dishonesty. Previous research has primarily focused on classifying text as either entirely human-written or LLM-generated, neglecting the detection of mixed texts that contain both types of content. This paper explores LLMs' ability to identify boundaries in human-written and machine-generated mixed texts. We approach this task by transforming it into a token classification problem and regard the label turning point as the boundary. Notably, our ensemble model of LLMs achieved first place in the 'Human-Machine Mixed Text Detection' sub-task of the SemEval'24 Competition Task 8. Additionally, we investigate factors that influence the capability of LLMs in detecting boundaries within mixed texts, including the incorporation of extra layers on top of LLMs, combination of segmentation loss, and the impact of pretraining. Our findings aim to provide valuable insights for future research in this area.

Coherence evaluation aims to assess the organization and structure of a discourse, which remains challenging even in the era of large language models. Due to the scarcity of annotated data, data augmentation is commonly used for training coherence evaluation models. However, previous augmentations for this task primarily rely on heuristic rules, lacking designing criteria as guidance. In this paper, we take inspiration from linguistic theory of discourse structure, and propose a data augmentation framework named CoUDA. CoUDA breaks down discourse coherence into global and local aspects, and designs augmentation strategies for both aspects, respectively. Especially for local coherence, we propose a novel generative strategy for constructing augmentation samples, which involves post-pretraining a generative model and applying two controlling mechanisms to control the difficulty of generated samples. During inference, CoUDA also jointly evaluates both global and local aspects to comprehensively assess the overall coherence of a discourse. Extensive experiments in coherence evaluation show that, with only 233M parameters, CoUDA achieves state-of-the-art performance in both pointwise scoring and pairwise ranking tasks, even surpassing recent GPT-3.5 and GPT-4 based metrics.

With the increasing use of robots in tasks involving humans in the perception-action loop, understanding the reasons behind failures in both planning and execution is a significant challenge for enhancing the reliability, adaptability, and safety of autonomous systems. Robots need to comprehend why and when failures occur and devise appropriate solutions based on the current situation. To achieve this, robots should be equipped with robust planning, perception, and reasoning capabilities enabling them to analyze failures and propose recovery strategies in real time. The standard approaches to autonomous robots are typically model-based or policy-based [3]. Model-based approaches can involve offline planning, where the robot considers the current state and utilizes its model to predict the next state and potential rewards, enabling it to plan a sequence of actions expected to maximize reward. In online model-based planning instead, the robot continuously re-plans based on the current state, adjusting its actions in response to changes in the environment. Policy-based approaches usually entail either open-loop policy, where the robot predicts a sequence of actions based on the initial state and goal, or closed-loop policy, where the robot predicts individual actions at each moment based on the current state and goal.

In this paper, we introduce a black-box prompt optimization method that uses an attacker LLM agent to uncover higher levels of memorization in a victim agent, compared to what is revealed by prompting the target model with the training data directly, which is the dominant approach of quantifying memorization in LLMs. We use an iterative rejection-sampling optimization process to find instruction-based prompts with two main characteristics: (1) minimal overlap with the training data to avoid presenting the solution directly to the model, and (2) maximal overlap between the victim model's output and the training data, aiming to induce the victim to spit out training data. We observe that our instruction-based prompts generate outputs with 23.7% higher overlap with training data compared to the baseline prefix-suffix measurements. Our findings show that (1) instruction-tuned models can expose pre-training data as much as their base-models, if not more so, (2) contexts other than the original training data can lead to leakage, and (3) using instructions proposed by other LLMs can open a new avenue of automated attacks that we should further study and explore. The code can be found at https://github.com/Alymostafa/Instruction_based_attack .

Despite the effectiveness of deep neural networks in numerous natural language processing applications, recent findings have exposed the vulnerability of these language models when minor perturbations are introduced. While appearing semantically indistinguishable to humans, these perturbations can significantly reduce the performance of well-trained language models, raising concerns about the reliability of deploying them in safe-critical situations. In this work, we construct a computationally efficient self-healing process to correct undesired model behavior during online inference when perturbations are applied to input data. This is formulated as a trajectory optimization problem in which the internal states of the neural network layers are automatically corrected using a PID (Proportional-Integral-Derivative) control mechanism. The P controller targets immediate state adjustments, while the I and D controllers consider past states and future dynamical trends, respectively. We leverage the geometrical properties of the training data to design effective linear PID controllers. This approach reduces the computational cost to that of using just the P controller, instead of the full PID control. Further, we introduce an analytical method for approximating the optimal control solutions, enhancing the real-time inference capabilities of this controlled system. Moreover, we conduct a theoretical error analysis of the analytic solution in a simplified setting. The proposed PID control-based self-healing is a low cost framework that improves the robustness of pre-trained large language models, whether standard or robustly trained, against a wide range of perturbations. A detailed implementation can be found in:https://github.com/zhuotongchen/PID-Control-Based-Self-Healing-to-Improve-the-Robustness-of-Large-Language-Models.

Language models pre-trained on general text have achieved impressive results in diverse fields. Yet, the distinct linguistic characteristics of task-oriented dialogues (TOD) compared to general text limit the practical utility of existing language models. Current task-oriented dialogue pre-training methods overlook the one-to-many property of conversations, where multiple responses can be appropriate given the same conversation context. In this paper, we propose a novel dialogue pre-training model called DivTOD, which collaborates with LLMs to learn diverse task-oriented dialogue representations. DivTOD guides LLMs in transferring diverse knowledge to smaller models while removing domain knowledge that contradicts task-oriented dialogues. Experiments show that our model outperforms strong TOD baselines on various downstream dialogue tasks and learns the intrinsic diversity of task-oriented dialogues.

The publication said it obtained a memo from House Chief Administrative Officer Catherine Szpindor, telling Congress personnel that the AI chatbot is now officially prohibited. Apparently, the Office of Cybersecurity has deemed Copilot to be a risk "due to the threat of leaking House data to non-House approved cloud services." While there's nothing stopping them from using Copilot on their own phones and laptops, it will now be blocked on all Windows devices owned by the Congress. Almost a year ago, the Congress also set a strict limit on the use of ChatGPT, which is powered by OpenAI's large language models, just like Copilot. It banned staffers from using the chatbot's free version on House computers, but it allowed them to continue using the paid (ChatGPT Plus) version for research and evaluation due to its tighter privacy controls.

OpenAI is sharing early results from a test for a feature that can read words aloud in a convincing human voice -- highlighting a new frontier for artificial intelligence and raising the specter of deepfake risks. The company is sharing early demos and use cases from a small-scale preview of the text-to-speech model, called Voice Engine, which it has shared with about 10 developers so far, a spokesperson said. OpenAI decided against a wider rollout of the feature, which it briefed reporters on earlier this month. A spokesperson for OpenAI said the company decided to scale back the release after receiving feedback from stakeholders such as policymakers, industry experts, educators and creatives. The company had initially planned to release the tool to as many as 100 developers through an application process, according to the earlier press briefing.

MindScape aims to study the benefits of integrating time series behavioral patterns (e.g., conversational engagement, sleep, location) with Large Language Models (LLMs) to create a new form of contextual AI journaling, promoting self-reflection and well-being. We argue that integrating behavioral sensing in LLMs will likely lead to a new frontier in AI. In this Late-Breaking Work paper, we discuss the MindScape contextual journal App design that uses LLMs and behavioral sensing to generate contextual and personalized journaling prompts crafted to encourage self-reflection and emotional development. We also discuss the MindScape study of college students based on a preliminary user study and our upcoming study to assess the effectiveness of contextual AI journaling in promoting better well-being on college campuses. MindScape represents a new application class that embeds behavioral intelligence in AI.

In the field of Natural Language Processing (NLP), Named Entity Recognition (NER) is recognized as a critical technology, employed across a wide array of applications. Traditional methodologies for annotating datasets for NER models are challenged by high costs and variations in dataset quality. This research introduces a novel hybrid annotation approach that synergizes human effort with the capabilities of Large Language Models (LLMs). This approach not only aims to ameliorate the noise inherent in manual annotations, such as omissions, thereby enhancing the performance of NER models, but also achieves this in a cost-effective manner. Additionally, by employing a label mixing strategy, it addresses the issue of class imbalance encountered in LLM-based annotations. Through an analysis across multiple datasets, this method has been consistently shown to provide superior performance compared to traditional annotation methods, even under constrained budget conditions. This study illuminates the potential of leveraging LLMs to improve dataset quality, introduces a novel technique to mitigate class imbalances, and demonstrates the feasibility of achieving high-performance NER in a cost-effective way.