Similar to the "previously-on" scenes in TV shows, recaps can help book reading by recalling the readers' memory about the important elements in previous texts to better understand the ongoing plot. Despite its usefulness, this application has not been well studied in the NLP community. We propose the first benchmark on this useful task called Recap Snippet Identification with a hand-crafted evaluation dataset. Our experiments show that the proposed task is challenging to PLMs, LLMs, and proposed methods as the task requires a deep understanding of the plot correlation between snippets.

The evaluation of text-generative vision-language models is a challenging yet crucial endeavor. By addressing the limitations of existing Visual Question Answering (VQA) benchmarks and proposing innovative evaluation methodologies, our research seeks to advance our understanding of these models' capabilities. We propose a novel VQA benchmark based on well-known visual classification datasets which allows a granular evaluation of text-generative vision-language models and their comparison with discriminative vision-language models. To improve the assessment of coarse answers on fine-grained classification tasks, we suggest using the semantic hierarchy of the label space to ask automatically generated follow-up questions about the ground-truth category. Finally, we compare traditional NLP and LLM-based metrics for the problem of evaluating model predictions given ground-truth answers. We perform a human evaluation study upon which we base our decision on the final metric. We apply our benchmark to a suite of vision-language models and show a detailed comparison of their abilities on object, action, and attribute classification. Our contributions aim to lay the foundation for more precise and meaningful assessments, facilitating targeted progress in the exciting field of vision-language modeling.

With the rise of online abuse, the NLP community has begun investigating the use of neural architectures to generate counterspeech that can "counter" the vicious tone of such abusive speech and dilute/ameliorate their rippling effect over the social network. However, most of the efforts so far have been primarily focused on English. To bridge the gap for low-resource languages such as Bengali and Hindi, we create a benchmark dataset of 5,062 abusive speech/counterspeech pairs, of which 2,460 pairs are in Bengali and 2,602 pairs are in Hindi. We implement several baseline models considering various interlingual transfer mechanisms with different configurations to generate suitable counterspeech to set up an effective benchmark. We observe that the monolingual setup yields the best performance. Further, using synthetic transfer, language models can generate counterspeech to some extent; specifically, we notice that transferability is better when languages belong to the same language family.

Large Language Models (LLMs) have demonstrated significant potential and effectiveness across multiple application domains. To assess the performance of mainstream LLMs in public security tasks, this study aims to construct a specialized evaluation benchmark tailored to the Chinese public security domain--CPSDbench. CPSDbench integrates datasets related to public security collected from real-world scenarios, supporting a comprehensive assessment of LLMs across four key dimensions: text classification, information extraction, question answering, and text generation. Furthermore, this study introduces a set of innovative evaluation metrics designed to more precisely quantify the efficacy of LLMs in executing tasks related to public security. Through the in-depth analysis and evaluation conducted in this research, we not only enhance our understanding of the performance strengths and limitations of existing models in addressing public security issues but also provide references for the future development of more accurate and customized LLM models targeted at applications in this field.

Natural language processing (NLP) is a key component of intelligent transportation systems (ITS), but it faces many challenges in the transportation domain, such as domain-specific knowledge and data, and multi-modal inputs and outputs. This paper presents TransGPT, a novel (multi-modal) large language model for the transportation domain, which consists of two independent variants: TransGPT-SM for single-modal data and TransGPT-MM for multi-modal data. TransGPT-SM is finetuned on a single-modal Transportation dataset (STD) that contains textual data from various sources in the transportation domain. TransGPT-MM is finetuned on a multi-modal Transportation dataset (MTD) that we manually collected from three areas of the transportation domain: driving tests, traffic signs, and landmarks. We evaluate TransGPT on several benchmark datasets for different tasks in the transportation domain, and show that it outperforms baseline models on most tasks. We also showcase the potential applications of TransGPT for traffic analysis and modeling, such as generating synthetic traffic scenarios, explaining traffic phenomena, answering traffic-related questions, providing traffic recommendations, and generating traffic reports. This work advances the state-of-the-art of NLP in the transportation domain and provides a useful tool for ITS researchers and practitioners.

Intention is an important and challenging concept in AI. It is important because it underlies many other concepts we care about, such as agency, manipulation, legal responsibility, and blame. However, ascribing intent to AI systems is contentious, and there is no universally accepted theory of intention applicable to AI agents. We operationalise the intention with which an agent acts, relating to the reasons it chooses its decision. We introduce a formal definition of intention in structural causal influence models, grounded in the philosophy literature on intent and applicable to real-world machine learning systems. Through a number of examples and results, we show that our definition captures the intuitive notion of intent and satisfies desiderata set-out by past work. In addition, we show how our definition relates to past concepts, including actual causality, and the notion of instrumental goals, which is a core idea in the literature on safe AI agents. Finally, we demonstrate how our definition can be used to infer the intentions of reinforcement learning agents and language models from their behaviour.

In this paper, we for the first time propose the task of Open-domain Urban Itinerary Planning (OUIP) for citywalk, which directly generates itineraries based on users' requests described in natural language. OUIP is different from conventional itinerary planning, which limits users from expressing more detailed needs and hinders true personalization. Recently, large language models (LLMs) have shown potential in handling diverse tasks. However, due to non-real-time information, incomplete knowledge, and insufficient spatial awareness, they are unable to independently deliver a satisfactory user experience in OUIP. Given this, we present ItiNera, an OUIP system that synergizes spatial optimization with Large Language Models (LLMs) to provide services that customize urban itineraries based on users' needs. Specifically, we develop an LLM-based pipeline for extracting and updating POI features to create a user-owned personalized POI database. For each user request, we leverage LLM in cooperation with an embedding-based module for retrieving candidate POIs from the user's POI database. Then, a spatial optimization module is used to order these POIs, followed by LLM crafting a personalized, spatially coherent itinerary. To the best of our knowledge, this study marks the first integration of LLMs to innovate itinerary planning solutions. Extensive experiments on offline datasets and online subjective evaluation have demonstrated the capacities of our system to deliver more responsive and spatially coherent itineraries than current LLM-based solutions. Our system has been deployed in production at the TuTu online travel service and has attracted thousands of users for their urban travel planning.

Large language models (LLMs) like ChatGPT, exhibit powerful zero-shot and instruction-following capabilities, have catalyzed a revolutionary transformation across diverse research fields of artificial intelligence, especially for open-ended tasks. While the idea is less explored in the graph domain, despite the availability of numerous powerful graph models (GMs), they are restricted to tasks in a pre-defined form. Although several methods applying LLMs to graphs have been proposed, they fail to simultaneously handle the pre-defined and open-ended tasks, with LLM as a node feature enhancer or as a standalone predictor. To break this dilemma, we propose to bridge the pretrained GM and LLM by a Translator, named GraphTranslator, aiming to leverage GM to handle the pre-defined tasks effectively and utilize the extended interface of LLMs to offer various open-ended tasks for GM. To train such Translator, we propose a Producer capable of constructing the graph-text alignment data along node information, neighbor information and model information. By treating the node representation as a type of language, the proposed GraphTranslator empowers an LLM to make predictions based on node representation and language instructions, providing a unified perspective for both pre-defined and open-ended tasks. Extensive results show that the proposed GraphTranslator effectively improves the results of zero-shot node classification. The graph question answering experiments reveal our GraphTranslator potential across a broad spectrum of open-ended applications through language instructions.

The robustness of large language models (LLMs) becomes increasingly important as their use rapidly grows in a wide range of domains. Retrieval-Augmented Generation (RAG) is considered as a means to improve the trustworthiness of text generation from LLMs. However, how the outputs from RAG-based LLMs are affected by slightly different inputs is not well studied. In this work, we find that the insertion of even a short prefix to the prompt leads to the generation of outputs far away from factually correct answers. We systematically evaluate the effect of such prefixes on RAG by introducing a novel optimization technique called Gradient Guided Prompt Perturbation (GGPP). GGPP achieves a high success rate in steering outputs of RAG-based LLMs to targeted wrong answers. It can also cope with instructions in the prompts requesting to ignore irrelevant context. We also exploit LLMs' neuron activation difference between prompts with and without GGPP perturbations to give a method that improves the robustness of RAG-based LLMs through a highly effective detector trained on neuron activation triggered by GGPP generated prompts. Our evaluation on open-sourced LLMs demonstrates the effectiveness of our methods.

Treatment planning is currently a patient specific, time-consuming, and resource demanding task in radiotherapy. Dose-volume histogram (DVH) prediction plays a critical role in automating this process. The geometric relationship between DVHs in radiotherapy plans and organs-at-risk (OAR) and planning target volume (PTV) has been well established. This study explores the potential of deep learning models for predicting DVHs using images and subsequent human intervention facilitated by a large-language model (LLM) to enhance the planning quality. We propose a pipeline to convert unstructured images to a structured graph consisting of image-patch nodes and dose nodes. A novel Dose Graph Neural Network (DoseGNN) model is developed for predicting DVHs from the structured graph. The proposed DoseGNN is enhanced with the LLM to encode massive knowledge from prescriptions and interactive instructions from clinicians. In this study, we introduced an online human-AI collaboration (OHAC) system as a practical implementation of the concept proposed for the automation of intensity-modulated radiotherapy (IMRT) planning. In comparison to the widely-employed DL models used in radiotherapy, DoseGNN achieved mean square errors that were 80$\%$, 76$\%$ and 41.0$\%$ of those predicted by Swin U-Net Transformer, 3D U-Net CNN and vanilla MLP, respectively. Moreover, the LLM-empowered DoseGNN model facilitates seamless adjustment to treatment plans through interaction with clinicians using natural language.