Social media imploded and the BBC practically ate itself last week as the scandal over Huw Edwards allegedly paying for explicit images from an unnamed young person unspooled. But what you knew, and when, depended largely on where you looked. Consume only traditional media – television, radio and newspapers and news websites like the Guardian – and you would not have had much inkling of who was in the frame until Edwards's wife named the BBC News presenter as the one at the centre of the storm. Sniff around social media, however, and you likely knew who was involved days before – and probably also thought a lot less of other names bandied about in connection with the concern. One former member of Twitter's curation team, who asked not to be named, believes the failure on Twitter's part was down to a combination of short-staffing and tech changes since Elon Musk took over.

In this paper, we propose an enhanced approach for Rapid Exploration and eXploitation for AI Agents called REX. Existing AutoGPT-style techniques have inherent limitations, such as a heavy reliance on precise descriptions for decision-making, and the lack of a systematic approach to leverage try-and-fail procedures akin to traditional Reinforcement Learning (RL). REX introduces an additional layer of rewards and integrates concepts similar to Upper Confidence Bound (UCB) scores, leading to more robust and efficient AI agent performance. This approach has the advantage of enabling the utilization of offline behaviors from logs and allowing seamless integration with existing foundation models while it does not require any model fine-tuning. Through comparative analysis with existing methods such as Chain-of-Thoughts(CoT) and Reasoning viA Planning(RAP), REX-based methods demonstrate comparable performance and, in certain cases, even surpass the results achieved by these existing techniques. Notably, REX-based methods exhibit remarkable reductions in execution time, enhancing their practical applicability across a diverse set of scenarios.

Transformer-based models have gained popularity in the field of natural language processing (NLP) and are extensively utilized in computer vision tasks and multi-modal models such as GPT4. This paper presents a novel method to enhance the explainability of Transformer-based image classification models. Our method aims to improve trust in classification results and empower users to gain a deeper understanding of the model for downstream tasks by providing visualizations of class-specific maps. We introduce two modules: the ``Relationship Weighted Out" and the ``Cut" modules. The ``Relationship Weighted Out" module focuses on extracting class-specific information from intermediate layers, enabling us to highlight relevant features. Additionally, the ``Cut" module performs fine-grained feature decomposition, taking into account factors such as position, texture, and color. By integrating these modules, we generate dense class-specific visual explainability maps. We validate our method with extensive qualitative and quantitative experiments on the ImageNet dataset. Furthermore, we conduct a large number of experiments on the LRN dataset, specifically designed for automatic driving danger alerts, to evaluate the explainability of our method in complex backgrounds. The results demonstrate a significant improvement over previous methods. Moreover, we conduct ablation experiments to validate the effectiveness of each module. Through these experiments, we are able to confirm the respective contributions of each module, thus solidifying the overall effectiveness of our proposed approach.

Music can evoke various emotions, and with the advancement of technology, it has become more accessible to people. Bangla music, which portrays different human emotions, lacks sufficient research. The authors of this article aim to analyze Bangla songs and classify their moods based on the lyrics. To achieve this, this research has compiled a dataset of 4000 Bangla song lyrics, genres, and used Natural Language Processing and the Bert Algorithm to analyze the data. Among the 4000 songs, 1513 songs are represented for the sad mood, 1362 for the romantic mood, 886 for happiness, and the rest 239 are classified as relaxation. By embedding the lyrics of the songs, the authors have classified the songs into four moods: Happy, Sad, Romantic, and Relaxed. This research is crucial as it enables a multi-class classification of songs' moods, making the music more relatable to people's emotions. The article presents the automated result of the four moods accurately derived from the song lyrics.

With the rapid evolution of large language models (LLMs), there is a growing concern that they may pose risks or have negative social impacts. Therefore, evaluation of human values alignment is becoming increasingly important. Previous work mainly focuses on assessing the performance of LLMs on certain knowledge and reasoning abilities, while neglecting the alignment to human values, especially in a Chinese context. In this paper, we present CValues, the first Chinese human values evaluation benchmark to measure the alignment ability of LLMs in terms of both safety and responsibility criteria. As a result, we have manually collected adversarial safety prompts across 10 scenarios and induced responsibility prompts from 8 domains by professional experts. To provide a comprehensive values evaluation of Chinese LLMs, we not only conduct human evaluation for reliable comparison, but also construct multi-choice prompts for automatic evaluation. Our findings suggest that while most Chinese LLMs perform well in terms of safety, there is considerable room for improvement in terms of responsibility. Moreover, both the automatic and human evaluation are important for assessing the human values alignment in different aspects. The benchmark and code is available on ModelScope and Github.

For a complicated algorithm, its implementation by a human programmer usually starts with outlining a rough control flow followed by iterative enrichments, eventually yielding carefully generated syntactic structures and variables in a hierarchy. However, state-of-the-art large language models generate codes in a single pass, without intermediate warm-ups to reflect the structured thought process of "outline-then-detail". Inspired by the recent success of chain-of-thought prompting, we propose ChainCoder, a program synthesis language model that generates Python code progressively, i.e. from coarse to fine in multiple passes. We first decompose source code into layout frame components and accessory components via abstract syntax tree parsing to construct a hierarchical representation. We then reform our prediction target into a multi-pass objective, each pass generates a subsequence, which is concatenated in the hierarchy. Finally, a tailored transformer architecture is leveraged to jointly encode the natural language descriptions and syntactically aligned I/O data samples. Extensive evaluations show that ChainCoder outperforms state-of-the-arts, demonstrating that our progressive generation eases the reasoning procedure and guides the language model to generate higher-quality solutions. Our codes are available at: https://github.com/VITA-Group/ChainCoder.

Modern language models can imitate complex patterns through few-shot learning, enabling them to complete challenging tasks without fine-tuning. However, imitation can also lead models to reproduce inaccuracies or harmful content if present in the context. We study harmful imitation through the lens of a model's internal representations, and identify two related phenomena: overthinking and false induction heads. The first phenomenon, overthinking, appears when we decode predictions from intermediate layers, given correct vs. incorrect few-shot demonstrations. At early layers, both demonstrations induce similar model behavior, but the behavior diverges sharply at some "critical layer", after which the accuracy given incorrect demonstrations progressively decreases. The second phenomenon, false induction heads, are a possible mechanistic cause of overthinking: these are heads in late layers that attend to and copy false information from previous demonstrations, and whose ablation reduces overthinking. Beyond scientific understanding, our results suggest that studying intermediate model computations could be a promising avenue for understanding and guarding against harmful model behaviors.

Human-AI interactivity is a critical aspect that reflects the usability of multimodal large language models (MLLMs). However, existing end-to-end MLLMs only allow users to interact with them through language instructions, leading to the limitation of the interactive accuracy and efficiency. In this study, we present precise referring instructions that utilize diverse reference representations such as points and boxes as referring prompts to refer to the special region. This enables MLLMs to focus on the region of interest and achieve finer-grained interaction. Based on precise referring instruction, we propose ChatSpot, a unified end-to-end multimodal large language model that supports diverse forms of interactivity including mouse clicks, drag-and-drop, and drawing boxes, which provides a more flexible and seamless interactive experience. We also construct a multi-grained vision-language instruction-following dataset based on existing datasets and GPT-4 generating. Furthermore, we design a series of evaluation tasks to assess the effectiveness of region recognition and interaction. Experimental results showcase ChatSpot's promising performance.

In recent years, large-scale pre-trained speech language models (SLMs) have demonstrated remarkable advancements in various generative speech modeling applications, such as text-to-speech synthesis, voice conversion, and speech enhancement. These applications typically involve mapping text or speech inputs to pre-trained SLM representations, from which target speech is decoded. This paper introduces a new approach, SLMGAN, to leverage SLM representations for discriminative tasks within the generative adversarial network (GAN) framework, specifically for voice conversion. Building upon StarGANv2-VC, we add our novel SLM-based WavLM discriminators on top of the mel-based discriminators along with our newly designed SLM feature matching loss function, resulting in an unsupervised zero-shot voice conversion system that does not require text labels during training. Subjective evaluation results show that SLMGAN outperforms existing state-of-the-art zero-shot voice conversion models in terms of naturalness and achieves comparable similarity, highlighting the potential of SLM-based discriminators for related applications.

As the probability (and thus perplexity) of a text is calculated based on the product of the probabilities of individual tokens, it may happen that one unlikely token significantly reduces the probability (i.e., increase the perplexity) of some otherwise highly probable input, while potentially representing a simple typographical error. Also, given that perplexity is a scalar value that refers to the entire input, information about the probability distribution within it is lost in the calculation (a relatively good text that has one unlikely token and another text in which each token is equally likely they can have the same perplexity value), especially for longer texts. As an alternative to scalar perplexity this research proposes a simple algorithm used to calculate vector values based on n-gram perplexities within the input. Such representations consider the previously mentioned aspects, and instead of a unique value, the relative perplexity of each text token is calculated, and these values are combined into a single vector representing the input.