Recently, the development of large language models (LLMs) has been significantly enhanced the question answering and dialogue generation, and makes them become increasingly popular in current practical scenarios. While unlike the general dialogue system which emphasizes the semantic performance, the task-oriented dialogue (ToD) systems aim to achieve the dialogue goal efficiently and successfully in multiple turns. Unfortunately, existing LLM-induced ToD systems lack the direct reward toward the final goal and do not take account of the dialogue proactivity that can strengthen the dialogue efficiency. To fill these gaps, we introduce the ProToD (Proactively Goal-Driven LLM-Induced ToD) approach, which anticipates the future dialogue actions and incorporates the goal-oriented reward signal to enhance ToD systems. Additionally, we present a novel evaluation method that assesses ToD systems based on goal-driven dialogue simulations. This method allows us to gauge user satisfaction, system efficiency and successful rate while overcoming the limitations of current Information and Success metrics. Empirical experiments conducted on the MultiWoZ 2.1 dataset demonstrate that our model can achieve superior performance using only 10% of the data compared to previous end-to-end fully supervised models. This improvement is accompanied by enhanced user satisfaction and efficiency.

In modern commercial search engines and recommendation systems, data from multiple domains is available to jointly train the multi-domain model. Traditional methods train multi-domain models in the multi-task setting, with shared parameters to learn the similarity of multiple tasks, and task-specific parameters to learn the divergence of features, labels, and sample distributions of individual tasks. With the development of large language models, LLM can extract global domain-invariant text features that serve both search and recommendation tasks. We propose a novel framework called S\&R Multi-Domain Foundation, which uses LLM to extract domain invariant features, and Aspect Gating Fusion to merge the ID feature, domain invariant text features and task-specific heterogeneous sparse features to obtain the representations of query and item. Additionally, samples from multiple search and recommendation scenarios are trained jointly with Domain Adaptive Multi-Task module to obtain the multi-domain foundation model. We apply the S\&R Multi-Domain foundation model to cold start scenarios in the pretrain-finetune manner, which achieves better performance than other SOTA transfer learning methods. The S\&R Multi-Domain Foundation model has been successfully deployed in Alipay Mobile Application's online services, such as content query recommendation and service card recommendation, etc.

We employ a tool-interacting divide-and-conquer strategy enabling large language models (LLMs) to answer complex multimodal multi-hop questions. In particular, we harness the power of large language models to divide a given multimodal multi-hop question into unimodal single-hop sub-questions to be answered by the appropriate tool from a predefined set of tools. After all corresponding tools provide the LLM with their answers, the LLM generates the next relevant unimodal single-hop question. To increase the reasoning ability of LLMs, we prompt chatGPT to generate a tool-interacting divide-and-conquer dataset. This dataset is then used to efficiently finetune the corresponding LLM. To assess the effectiveness of this approach, we conduct an evaluation on two recently introduced complex question-answering datasets. The experimental analysis demonstrate substantial improvements over existing state-of-the-art solutions, indicating the efficacy and generality of our strategy

The emergence of human-like abilities of AI systems for content generation in domains such as text, audio, and vision has prompted the development of classifiers to determine whether content originated from a human or a machine. Implicit in these efforts is an assumption that the generation properties of a human are different from that of the machine. In this work, we provide a framework in the language of statistical pattern recognition that quantifies the difference between the distributions of human and machine-generated content conditioned on an evaluation context. We describe current methods in the context of the framework and demonstrate how to use the framework to evaluate the progression of generative models towards human-like capabilities, among many axes of analysis.

LLMs are increasingly powerful and widely used to assist users in a variety of tasks. This use risks the introduction of LLM biases to consequential decisions such as job hiring, human performance evaluation, and criminal sentencing. Bias in NLP systems along the lines of gender and ethnicity has been widely studied, especially for specific stereotypes (e.g., Asians are good at math). In this paper, we investigate bias along less studied, but still consequential, dimensions, such as age and beauty, measuring subtler correlated decisions that LLMs (specially autoregressive language models) make between social groups and unrelated positive and negative attributes. We ask whether LLMs hold wide-reaching biases of positive or negative sentiment for specific social groups similar to the ``what is beautiful is good'' bias found in people in experimental psychology. We introduce a template-generated dataset of sentence completion tasks that asks the model to select the most appropriate attribute to complete an evaluative statement about a person described as a member of a specific social group. We also reverse the completion task to select the social group based on an attribute. Finally, we report the correlations that we find for multiple cutting-edge LLMs. This dataset can be used as a benchmark to evaluate progress in more generalized biases and the templating technique can be used to expand the benchmark with minimal additional human annotation.

ChatGPT-4 with Code Interpreter can be used to solve introductory college-level vector calculus and electromagnetism problems Tanuj Kumar (tanuj.kumar@wisc.edu) Executive summary: We evaluated three modes of ChatGPT -- 3.5, 4, and 4 with Code Interpreter -- on a set of college-level engineering-math and electromagnetism problems, such as those often given to sophomore electrical engineering majors. We selected a set of 13 problems without first testing them with ChatGPT, and had ChatGPT solve them multiple times, using a fresh instance (chat) of ChatGPT each time. The problems range from elementary to medium-level. We were strict in our evaluation of ChatGPT's performance, marking a solution as incorrect if even a small part of the solution was wrong. Our major conclusions are: ChatGPT-4 with Code Interpreter (ChatGPT-4/CI), recently renamed Advanced Data Analysis, was able to satisfactorily solve most problems we tested most of the time. Qualitatively, one could give ChatGPT-4/CI a solid passing grade in introductory engineering math and electromagnetics.

Understanding when two pieces of text convey the same information is a goal touching many subproblems in NLP, including textual entailment and fact-checking. This problem becomes more complex when those two pieces of text are in different languages. Here, we introduce X-PARADE (Cross-lingual Paragraph-level Analysis of Divergences and Entailments), the first cross-lingual dataset of paragraph-level information divergences. Annotators label a paragraph in a target language at the span level and evaluate it with respect to a corresponding paragraph in a source language, indicating whether a given piece of information is the same, new, or new but can be inferred. This last notion establishes a link with cross-language NLI. Aligned paragraphs are sourced from Wikipedia pages in different languages, reflecting real information divergences observed in the wild. Armed with our dataset, we investigate a diverse set of approaches for this problem, including classic token alignment from machine translation, textual entailment methods that localize their decisions, and prompting of large language models. Our results show that these methods vary in their capability to handle inferable information, but they all fall short of human performance.

Multi-modal large language models have garnered significant interest recently. Though, most of the works focus on vision-language multi-modal models providing strong capabilities in following vision-and-language instructions. However, we claim that speech is also an important modality through which humans interact with the world. Hence, it is crucial for a general-purpose assistant to be able to follow multi-modal speech-and-language instructions. In this work, we propose Large Language and Speech Model (LLaSM). LLaSM is an end-to-end trained large multi-modal speech-language model with cross-modal conversational abilities, capable of following speech-and-language instructions. Our early experiments show that LLaSM demonstrates a more convenient and natural way for humans to interact with artificial intelligence. Specifically, we also release a large Speech Instruction Following dataset LLaSM-Audio-Instructions. Code and demo are available at https://github.com/LinkSoul-AI/LLaSM and https://huggingface.co/spaces/LinkSoul/LLaSM. The LLaSM-Audio-Instructions dataset is available at https://huggingface.co/datasets/LinkSoul/LLaSM-Audio-Instructions.

ChatGPT has proven it can help students with their homework, but now it is helping teachers create those very courses, a computer science professor told Fox News. I'm still amazed at how ChatGPT can help write a toast to put people in stitches at a wedding, construct a legal argument to bolster a case and even help with a college admissions essay despite the number of errors the human eye can catch. Even with the glitches, using a chatbot still astounds most people who manage to put in perfect prompts to get wildly in-depth instant answers. And while OpenAI's ChatGPT is impressive, it's not the only option you should be confined to using. In fact, some of the biggest tech companies in the world are competing to create their own latest and greatest chatbots that can rival or surpass the AI amazement of ChatGPT.

Suleyman has had an unshaken faith in technology as a force for good at least since we first spoke in early 2016. He had just launched DeepMind Health and set up research collaborations with some of the UK's state-run regional health-care providers. The magazine I worked for at the time was about to publish an article claiming that DeepMind had failed to comply with data protection regulations when accessing records from some 1.6 million patients to set up those collaborations--a claim later backed up by a government investigation. Suleyman couldn't see why we would publish a story that was hostile to his company's efforts to improve health care. As long as he could remember, he told me at the time, he'd only wanted to do good in the world.