Language models (LMs) have demonstrated remarkable capabilities in NLP, yet adapting them efficiently and robustly to specific tasks remains challenging. As their scale and complexity grow, fine-tuning LMs on labelled data often underutilizes available unlabelled data, leads to overfitting on small task-specific sets, and imposes significant computational costs. These limitations hamper their application to the open-ended landscape of real-world language tasks. This thesis proposes a series of methods to better adapt LMs to downstream applications. First, we explore strategies for extracting task-relevant knowledge from unlabelled data, introducing a novel continued pre-training technique that outperforms state-of-the-art semi-supervised approaches. Next, we present a parameter-efficient fine-tuning method that substantially reduces memory and compute costs while maintaining competitive performance. We also introduce improved supervised fine-tuning methods that enable LMs to better follow instructions, especially when labelled data is scarce, enhancing their performance across a range of NLP tasks, including open-ended generation. Finally, we develop new evaluation methods and benchmarks, such as multi-hop spatial reasoning tasks, to assess LM capabilities and adaptation more comprehensively. Through extensive empirical studies across diverse NLP tasks, our results demonstrate that these approaches substantially improve LM robustness, efficiency, and generalization, making them more adaptable to a broad range of applications. These advances mark a significant step towards more robust and efficient LMs, bringing us closer to the goal of artificial general intelligence.

Papers published in top conferences contribute influential discoveries that are reshaping the landscape of modern Artificial Intelligence (AI). We analyzed 87,137 papers from 11 AI conferences to examine publication trends over the past decade. Our findings reveal a consistent increase in both the number of papers and authors, reflecting the growing interest in AI research. We also observed a rise in prolific researchers who publish dozens of papers at the same conference each year. In light of this analysis, the AI research community should consider revisiting authorship policies, addressing equity concerns, and evaluating the workload of junior researchers to foster a more sustainable and inclusive research environment.

Large language models (LLMs) have demonstrated remarkable capabilities across a broad spectrum of tasks. They have attracted significant attention and been deployed in numerous downstream applications. Nevertheless, akin to a double-edged sword, LLMs also present potential risks. They could suffer from private data leaks or yield inappropriate, harmful, or misleading content. Additionally, the rapid progress of LLMs raises concerns about the potential emergence of superintelligent systems without adequate safeguards. To effectively capitalize on LLM capacities as well as ensure their safe and beneficial development, it is critical to conduct a rigorous and comprehensive evaluation of LLMs. This survey endeavors to offer a panoramic perspective on the evaluation of LLMs. We categorize the evaluation of LLMs into three major groups: knowledge and capability evaluation, alignment evaluation and safety evaluation. In addition to the comprehensive review on the evaluation methodologies and benchmarks on these three aspects, we collate a compendium of evaluations pertaining to LLMs' performance in specialized domains, and discuss the construction of comprehensive evaluation platforms that cover LLM evaluations on capabilities, alignment, safety, and applicability. We hope that this comprehensive overview will stimulate further research interests in the evaluation of LLMs, with the ultimate goal of making evaluation serve as a cornerstone in guiding the responsible development of LLMs. We envision that this will channel their evolution into a direction that maximizes societal benefit while minimizing potential risks. A curated list of related papers has been publicly available at https://github.com/tjunlp-lab/Awesome-LLMs-Evaluation-Papers.

It has been noticed that through COVID-19 greenhouse gas emissions had a sudden reduction. Based on this significant observation, we decided to conduct a research to quantify the impact of scientific conferences' air-travelling, explore and suggest alternative ways for greener conferences to re-duce the global carbon footprint. Specifically, we focused on the most popular conferences for the Artificial Intelligence community based on their scientific impact factor, their scale, and the well-organized proceedings towards measuring the impact of air travelling participation. This is the first time that systematic quantification of a state-of-the-art subject like Artificial Intelligence takes place to define its conferencing footprint in the broader frames of environmental awareness. Our findings highlight that the virtual way is the first on the list of green conferences' conduction although there are serious concerns about it. Alternatives to optimal conferences' location selection have demonstrated savings on air-travelling CO2 emissions of up to 63.9%.

This dissertation proposes a framework of user-centered security in Natural Language Processing (NLP), and demonstrates how it can improve the accessibility of related research. Accordingly, it focuses on two security domains within NLP with great public interest. First, that of author profiling, which can be employed to compromise online privacy through invasive inferences. Without access and detailed insight into these models' predictions, there is no reasonable heuristic by which Internet users might defend themselves from such inferences. Secondly, that of cyberbullying detection, which by default presupposes a centralized implementation; i.e., content moderation across social platforms. As access to appropriate data is restricted, and the nature of the task rapidly evolves (both through lexical variation, and cultural shifts), the effectiveness of its classifiers is greatly diminished and thereby often misrepresented. Under the proposed framework, we predominantly investigate the use of adversarial attacks on language; i.e., changing a given input (generating adversarial samples) such that a given model does not function as intended. These attacks form a common thread between our user-centered security problems; they are highly relevant for privacy-preserving obfuscation methods against author profiling, and adversarial samples might also prove useful to assess the influence of lexical variation and augmentation on cyberbullying detection.

Artificial Intelligence conferences organized by ScienceFather group. ScienceFather takes the privilege to invite speakers, participants, students, delegates, and exhibitors from across the globe to its Global Conference on Artificial Intelligence conferences to be held in the Various Beautiful cites of the world. Artificial Intelligence conferences are a discussion of common Inventions-related issues and additionally trade information, share proof, thoughts, and insight into advanced developments in the science inventions service system. New technology may create many materials and devices with a vast range of applications, such as in Science, medicine, electronics, biomaterials, energy production, and consumer products. The focal point of Artificial Intelligence is to bring forward discoveries, examine the system and strategic issues, assemble and keep forth basic strategies between analysts, professionals, arrangement producers, and agents of science Associations.

Deep learning has become the dominant approach in coping with various tasks in Natural Language Processing (NLP). Although text inputs are typically represented as a sequence of tokens, there is a rich variety of NLP problems that can be best expressed with a graph structure. As a result, there is a surge of interests in developing new deep learning techniques on graphs for a large number of NLP tasks. In this survey, we present a comprehensive overview on Graph Neural Networks (GNNs) for Natural Language Processing. We propose a new taxonomy of GNNs for NLP, which systematically organizes existing research of GNNs for NLP along three axes: graph construction, graph representation learning, and graph based encoder-decoder models. We further introduce a large number of NLP applications that are exploiting the power of GNNs and summarize the corresponding benchmark datasets, evaluation metrics, and open-source codes. Finally, we discuss various outstanding challenges for making the full use of GNNs for NLP as well as future research directions. To the best of our knowledge, this is the first comprehensive overview of Graph Neural Networks for Natural Language Processing.

I've attended a few conferences on artificial intelligence (AI), but one last week drove home some concepts to discuss. While it might seem I'm picking on The University of Texas, Austin, McCombs School of Business, I'm not. All their CATT 2021 Global Analytics Summit did is clarify some ideas. The key problem is that conference organizers don't seem to be clearly differentiating between two different business audiences. There are two very different business audiences interested in AI.

How companies can get started with AI The program for our Artificial Intelligence Conference in London is structured to help companies that are still very much in the early stages of AI adoption. Judging by the list of countries putting out policy papers on AI and automation technologies there is very strong interest in AI across the globe. In order to asses the current state of readiness across regions we recently conducted a survey (full report forthcoming) of the state of adoption of machine learning tools and technologies (a lot of what is being currently described as AI is really ML). The survey yielded 11400 respondents including 2000 respondents from Europe: As we assembled the program for our inaugural Artificial Intelligence Conference in London this October we recognized that many companies and organizations around the world are still very much in the early stages of adoption. Anyone wanting to get started on AI technologies will have to wade through an array of methods and technologies many of which are still very much on the leading edge.

Unprecedented advancements in technology and the growing complexity of the world's research challenges demand novel approaches to discovery and innovation. One way for leaders in STEM to stay ahead of this curve is by attending the nation's top tech conferences. These conferences are an excellent chance for STEM professionals to develop valuable connections, exchange groundbreaking ideas, share best practices, and learn new skills while staying abreast of emerging trends and practices in the ever-evolving technology landscape. However, with dozens of conferences to choose from, it can be challenging to select the right one for your organization. And, with the emergence of the COVID-19 global pandemic, it has become difficult to accurately plan for future events.