Large Language Models (LLMs) need to be aligned with human expectations to ensure their safety and utility in most applications. Alignment is challenging, costly, and needs to be repeated for every LLM and alignment criterion. We propose to decouple LLMs and alignment by training aligner models that can be used to align any LLM for a given criteria on an as-needed basis, thus also reducing the potential negative impacts of alignment on performance. Our recipe for training the aligner models solely relies on synthetic data generated with a (prompted) LLM and can be easily adjusted for a variety of alignment criteria. We use the same synthetic data to train inspectors, binary miss-alignment classification models to guide a "squad" of multiple aligners. Our empirical results demonstrate consistent improvements when applying aligner squad to various LLMs, including chat-aligned models, across several instruction-following and red-teaming datasets.

Kullback-Leiber divergence has been widely used in Knowledge Distillation (KD) to compress Large Language Models (LLMs). Contrary to prior assertions that reverse Kullback-Leibler (RKL) divergence is mode-seeking and thus preferable over the mean-seeking forward Kullback-Leibler (FKL) divergence, this study empirically and theoretically demonstrates that neither mode-seeking nor mean-seeking properties manifest in KD for LLMs. Instead, RKL and FKL are found to share the same optimization objective and both converge after a sufficient number of epochs. However, due to practical constraints, LLMs are seldom trained for such an extensive number of epochs. Meanwhile, we further find that RKL focuses on the tail part of the distributions, while FKL focuses on the head part at the beginning epochs. Consequently, we propose a simple yet effective Adaptive Kullback-Leiber (AKL) divergence method, which adaptively allocates weights to combine FKL and RKL. Metric-based and GPT-4-based evaluations demonstrate that the proposed AKL outperforms the baselines across various tasks and improves the diversity and quality of generated responses.

Indirect User Requests (IURs), such as "It's cold in here" instead of "Could you please increase the temperature?" are common in human-human task-oriented dialogue and require world knowledge and pragmatic reasoning from the listener. While large language models (LLMs) can handle these requests effectively, smaller models deployed on virtual assistants often struggle due to resource constraints. Moreover, existing task-oriented dialogue benchmarks lack sufficient examples of complex discourse phenomena such as indirectness. To address this, we propose a set of linguistic criteria along with an LLM-based pipeline for generating realistic IURs to test natural language understanding (NLU) and dialogue state tracking (DST) models before deployment in a new domain. We also release IndirectRequests, a dataset of IURs based on the Schema Guided Dialog (SGD) corpus, as a comparative testbed for evaluating the performance of smaller models in handling indirect requests.

The desire and ability to seek new information strategically are fundamental to human learning but often overlooked in current language agent evaluation. We analyze a popular web shopping task designed to test language agents' ability to perform strategic exploration and discover that it can be reformulated and solved as a single-turn retrieval task without the need for interactive information seeking. This finding encourages us to rethink realistic constraints on information access that would necessitate strategic information seeking. We then redesign the task to introduce a notion of task ambiguity and the role of a shopper, serving as a dynamic party with whom the agent strategically interacts in an open-ended conversation to make informed decisions. Our experiments demonstrate that the proposed task can effectively evaluate the agent's ability to explore and gradually accumulate information through multi-turn interactions. Additionally, we show that large language model-simulated shoppers serve as a good proxy for real human shoppers, revealing similar error patterns in agents.

Recent pandemics have highlighted vulnerabilities in our global economic systems, especially supply chains. Possible future pandemic raises a dilemma for businesses owners between short-term profitability and long-term supply chain resilience planning. In this study, we propose a novel agent-based simulation model integrating extended Susceptible-Infected-Recovered (SIR) epidemiological model and supply and demand economic model to evaluate supply chain resilience strategies during pandemics. Using this model, we explore a range of supply chain resilience strategies under pandemic scenarios using in silico experiments. We find that a balanced approach to supply chain resilience performs better in both pandemic and non-pandemic times compared to extreme strategies, highlighting the importance of preparedness in the form of a better supply chain resilience. However, our analysis shows that the exact supply chain resilience strategy is hard to obtain for each firm and is relatively sensitive to the exact profile of the pandemic and economic state at the beginning of the pandemic. As such, we used a machine learning model that uses the agent-based simulation to estimate a near-optimal supply chain resilience strategy for a firm. The proposed model offers insights for policymakers and businesses to enhance supply chain resilience in the face of future pandemics, contributing to understanding the trade-offs between short-term gains and long-term sustainability in supply chain management before and during pandemics.

Large language models (LLMs) have achieved remarkable progress in many natural language processing tasks. However, our experiment reveals that, in stance detection tasks, LLMs may generate biased stances due to sentiment-stance spurious correlations and preference towards certain individuals and topics, thus harming their performance. Therefore, in this paper, we propose to Mitigate Biases of LLMs in stance detection with Calibration (MB-Cal). To be specific, a novel calibration network is devised to calibrate potential bias in the stance prediction of LLMs. Further, to address the challenge of effectively learning bias representations and the difficulty in the generalizability of debiasing, we construct counterfactual augmented data. This approach enhances the calibration network, facilitating the debiasing and out-of-domain generalization. Experimental results on in-target and zero-shot stance detection tasks show that the proposed MB-Cal can effectively mitigate biases of LLMs, achieving state-of-the-art results.

In his classic novel, 1984, George Orwell imagined how Britain might one day become a totalitarian surveillance state. Yet as Orwell's novel celebrates its 75th anniversary this month, British police are already deploying technologies that would put Big Brother to shame. From the facial recognition cameras watching you shop to the algorithms predicting crimes before they happen, these tools feel as if they've been ripped from the pages of science fiction. But there is nothing fictional about the AI cops already patrolling Britain's streets - and experts say there is only more to come. Jake Hufurt, head of research and investigations at Big Brother Watch, warned MailOnline: 'We're sleepwalking into a high-tech police state.'

In the village of Ndodo, 40 kilometers south of the Malawian capital Lilongwe, farmers gather in the shade of an acacia tree as a voice over a smartphone tells them how to get rid of a weevil that's destroying their sweet potato crops. The tips offered by the app in the local language Chichewa is one of the first examples of how artificial intelligence is being used to aid subsistence farmers in some of the poorest parts of the world. Piloted by a Chicago-based nonprofit organization Opportunity International, the app called Ulangizi -- which translates as "Advice" -- works on WhatsApp and uses data from ChatGPT and the Malawian government's English-language agricultural manual to answer questions or diagnose crop and farm animal diseases. "The majority of our people do not know how to read or write," said Anna Chimalizeni, a 36-year-old mother of three, who as a government farmer-support agent demonstrates the app to farmers. "I am there to help them write issues they have at their farms and read the response on their behalf. They also have a chance to listen to the response through voice notes which come in our own local language."

Artificial intelligence (AI) as a disruptive technology is not new. However, its recent evolution, engineered by technological transformation, big data analytics, and quantum computing, produces conversational and generative AI (CGAI/GenAI) and human-like chatbots that disrupt conventional operations and methods in different fields. This study investigates the scientific landscape of CGAI and human-chatbot interaction/collaboration and evaluates use cases, benefits, challenges, and policy implications for multidisciplinary education and allied industry operations. The publications trend showed that just 4% (n=75) occurred during 2006-2018, while 2019-2023 experienced astronomical growth (n=1763 or 96%). The prominent use cases of CGAI (e.g., ChatGPT) for teaching, learning, and research activities occurred in computer science [multidisciplinary and AI] (32%), medical/healthcare (17%), engineering (7%), and business fields (6%). The intellectual structure shows strong collaboration among eminent multidisciplinary sources in business, Information Systems, and other areas. The thematic structure of SLP highlights prominent CGAI use cases, including improved user experience in human-computer interaction, computer programs/code generation, and systems creation. Widespread CGAI usefulness for teachers, researchers, and learners includes syllabi/course content generation, testing aids, and academic writing. The concerns about abuse and misuse (plagiarism, academic integrity, privacy violations) and issues about misinformation, danger of self-diagnoses, and patient privacy in medical/healthcare applications are prominent. Formulating strategies and policies to address potential CGAI challenges in teaching/learning and practice are priorities. Developing discipline-based automatic detection of GenAI contents to check abuse is proposed.

Text-to-image generation models often struggle with key element loss or semantic confusion in tasks involving Chinese classical poetry.Addressing this issue through fine-tuning models needs considerable training costs. Additionally, manual prompts for re-diffusion adjustments need professional knowledge. To solve this problem, we propose Poetry2Image, an iterative correction framework for images generated from Chinese classical poetry. Utilizing an external poetry dataset, Poetry2Image establishes an automated feedback and correction loop, which enhances the alignment between poetry and image through image generation models and subsequent re-diffusion modifications suggested by large language models (LLM). Using a test set of 200 sentences of Chinese classical poetry, the proposed method--when integrated with five popular image generation models--achieves an average element completeness of 70.63%, representing an improvement of 25.56% over direct image generation. In tests of semantic correctness, our method attains an average semantic consistency of 80.09%. The study not only promotes the dissemination of ancient poetry culture but also offers a reference for similar non-fine-tuning methods to enhance LLM generation.