Finding ways to accelerate text input for individuals with profound motor impairments has been a long-standing area of research. Closing the speed gap for augmentative and alternative communication (AAC) devices such as eye-tracking keyboards is important for improving the quality of life for such individuals. Recent advances in neural networks of natural language pose new opportunities for re-thinking strategies and user interfaces for enhanced text-entry for AAC users. In this paper, we present SpeakFaster, consisting of large language models (LLMs) and a co-designed user interface for text entry in a highly-abbreviated form, allowing saving 57% more motor actions than traditional predictive keyboards in offline simulation. A pilot study with 19 non-AAC participants typing on a mobile device by hand demonstrated gains in motor savings in line with the offline simulation, while introducing relatively small effects on overall typing speed. Lab and field testing on two eye-gaze typing users with amyotrophic lateral sclerosis (ALS) demonstrated text-entry rates 29-60% faster than traditional baselines, due to significant saving of expensive keystrokes achieved through phrase and word predictions from context-aware LLMs. These findings provide a strong foundation for further exploration of substantially-accelerated text communication for motor-impaired users and demonstrate a direction for applying LLMs to text-based user interfaces.

The benefits and capabilities of pre-trained language models (LLMs) in current and future innovations are vital to any society. However, introducing and using LLMs comes with biases and discrimination, resulting in concerns about equality, diversity and fairness, and must be addressed. While understanding and acknowledging bias in LLMs and developing mitigation strategies are crucial, the generalised assumptions towards societal needs can result in disadvantages towards under-represented societies and indigenous populations. Furthermore, the ongoing changes to actual and proposed amendments to regulations and laws worldwide also impact research capabilities in tackling the bias problem. This research presents a comprehensive survey synthesising the current trends and limitations in techniques used for identifying and mitigating bias in LLMs, where the overview of methods for tackling bias are grouped into metrics, benchmark datasets, and mitigation strategies. The importance and novelty of this survey are that it explores the perspective of under-represented societies. We argue that current practices tackling the bias problem cannot simply be 'plugged in' to address the needs of under-represented societies. We use examples from New Zealand to present requirements for adopting existing techniques to under-represented societies.

Writing radiology reports from medical images requires a high level of domain expertise. It is time-consuming even for trained radiologists and can be error-prone for inexperienced radiologists. It would be appealing to automate this task by leveraging generative AI, which has shown drastic progress in vision and language understanding. In particular, Large Language Models (LLM) have demonstrated impressive capabilities recently and continued to set new state-of-the-art performance on almost all natural language tasks. While many have proposed architectures to combine vision models with LLMs for multimodal tasks, few have explored practical fine-tuning strategies. In this work, we proposed a simple yet effective two-stage fine-tuning protocol to align visual features to LLM's text embedding space as soft visual prompts. Our framework with OpenLLaMA-7B achieved state-of-the-art level performance without domain-specific pretraining. Moreover, we provide detailed analyses of soft visual prompts and attention mechanisms, shedding light on future research directions.

Object rearrangement, a fundamental challenge in robotics, demands versatile strategies to handle diverse objects, configurations, and functional needs. To achieve this, the AI robot needs to learn functional rearrangement priors in order to specify precise goals that meet the functional requirements. Previous methods typically learn such priors from either laborious human annotations or manually designed heuristics, which limits scalability and generalization. In this work, we propose a novel approach that leverages large models to distill functional rearrangement priors. Specifically, our approach collects diverse arrangement examples using both LLMs and VLMs and then distills the examples into a diffusion model. During test time, the learned diffusion model is conditioned on the initial configuration and guides the positioning of objects to meet functional requirements. In this manner, we create a handshaking point that combines the strengths of conditional generative models and large models. Extensive experiments on multiple domains, including real-world scenarios, demonstrate the effectiveness of our approach in generating compatible goals for object rearrangement tasks, significantly outperforming baseline methods.

We present RobotGPT, an innovative decision framework for robotic manipulation that prioritizes stability and safety. The execution code generated by ChatGPT cannot guarantee the stability and safety of the system. ChatGPT may provide different answers for the same task, leading to unpredictability. This instability prevents the direct integration of ChatGPT into the robot manipulation loop. Although setting the temperature to 0 can generate more consistent outputs, it may cause ChatGPT to lose diversity and creativity. Our objective is to leverage ChatGPT's problem-solving capabilities in robot manipulation and train a reliable agent. The framework includes an effective prompt structure and a robust learning model. Additionally, we introduce a metric for measuring task difficulty to evaluate ChatGPT's performance in robot manipulation. Furthermore, we evaluate RobotGPT in both simulation and real-world environments. Compared to directly using ChatGPT to generate code, our framework significantly improves task success rates, with an average increase from 38.5% to 91.5%. Therefore, training a RobotGPT by utilizing ChatGPT as an expert is a more stable approach compared to directly using ChatGPT as a task planner.

Commercial contracts are known to be a valuable source for deriving project-specific requirements. However, contract negotiations mainly occur among the legal counsel of the parties involved. The participation of non-legal stakeholders, including requirement analysts, engineers, and solution architects, whose primary responsibility lies in ensuring the seamless implementation of contractual terms, is often indirect and inadequate. Consequently, a significant number of sentences in contractual clauses, though legally accurate, can appear unfair from an implementation perspective to non-legal stakeholders. This perception poses a problem since requirements indicated in the clauses are obligatory and can involve punitive measures and penalties if not implemented as committed in the contract. Therefore, the identification of potentially unfair clauses in contracts becomes crucial. In this work, we conduct an empirical study to analyze the perspectives of different stakeholders regarding contractual fairness. We then investigate the ability of Pre-trained Language Models (PLMs) to identify unfairness in contractual sentences by comparing chain of thought prompting and semi-supervised fine-tuning approaches. Using BERT-based fine-tuning, we achieved an accuracy of 84% on a dataset consisting of proprietary contracts. It outperformed chain of thought prompting using Vicuna-13B by a margin of 9%.

Deceptive agents are a challenge for the safety, trustworthiness, and cooperation of AI systems. We focus on the problem that agents might deceive in order to achieve their goals (for instance, in our experiments with language models, the goal of being evaluated as truthful). There are a number of existing definitions of deception in the literature on game theory and symbolic AI, but there is no overarching theory of deception for learning agents in games. We introduce a formal definition of deception in structural causal games, grounded in the philosophy literature, and applicable to real-world machine learning systems. Several examples and results illustrate that our formal definition aligns with the philosophical and commonsense meaning of deception. Our main technical result is to provide graphical criteria for deception. We show, experimentally, that these results can be used to mitigate deception in reinforcement learning agents and language models.

Recent advancements in Generative Language Models (GLMs) have transformed Natural Language Processing (NLP) by showcasing the effectiveness of the "pre-train, prompt, and predict" paradigm in utilizing pre-trained GLM knowledge for diverse applications. Despite their potential, these capabilities lack adequate quantitative characterization due to the absence of comprehensive benchmarks, particularly for low-resource languages. Existing low-resource benchmarks focus on discriminative language models like BERT, neglecting the evaluation of generative language models. Moreover, current benchmarks often overlook measuring generalization performance across multiple tasks, a crucial metric for GLMs. To bridge these gaps, we introduce NLEBench, a comprehensive benchmark tailored for evaluating natural language generation capabilities in Norwegian, a low-resource language. We use Norwegian as a case study to explore whether current GLMs and benchmarks in mainstream languages like English can reveal the unique characteristics of underrepresented languages. NLEBench encompasses a suite of real-world NLP tasks ranging from news storytelling, summarization, open-domain conversation, natural language understanding, instruction fine-tuning, toxicity and bias evaluation, to self-curated Chain-of-Thought investigation. It features two high-quality, human-annotated datasets: an instruction dataset covering traditional Norwegian cultures, idioms, slang, and special expressions, and a document-grounded multi-label dataset for topic classification, question answering, and summarization. This paper also introduces foundational Norwegian Generative Language Models (NorGLMs) developed with diverse parameter scales and Transformer-based architectures. Systematic evaluations on the proposed benchmark suite provide insights into the capabilities and scalability of NorGLMs across various downstream tasks.

Recent language models generate false but plausible-sounding text with surprising frequency. Such "hallucinations" are an obstacle to the usability of language-based AI systems and can harm people who rely upon their outputs. This work shows shows that there is an inherent statistical lower-bound on the rate that pretrained language models hallucinate certain types of facts, having nothing to do with the transformer LM architecture or data quality. For "arbitrary" facts whose veracity cannot be determined from the training data, we show that hallucinations must occur at a certain rate for language models that satisfy a statistical calibration condition appropriate for generative language models. Specifically, if the maximum probability of any fact is bounded, we show that the probability of generating a hallucination is close to the fraction of facts that occur exactly once in the training data (a "Good-Turing" estimate), even assuming ideal training data without errors. One conclusion is that models pretrained to be sufficiently good predictors (i.e., calibrated) may require post-training to mitigate hallucinations on the type of arbitrary facts that tend to appear once in the training set. However, our analysis also suggests that there is no statistical reason that pretraining will lead to hallucination on facts that tend to appear more than once in the training data (like references to publications such as articles and books, whose hallucinations have been particularly notable and problematic) or on systematic facts (like arithmetic calculations). Therefore, different architectures and learning algorithms may mitigate these latter types of hallucinations.

It results in more factual rationales and reduced hallucination in generation. Specifically, CoK consists of three stages: reasoning preparation, dynamic knowledge adapting, and answer consolidation. Given a knowledge-intensive question, CoK first prepares several preliminary rationales and answers while identifying the relevant knowledge domains. If there is no majority consensus among the answers from samples, CoK corrects the rationales step by step by adapting knowledge from the identified domains. These corrected rationales can plausibly serve as a better foundation for the final answer consolidation. Unlike prior studies that primarily use unstructured data, CoK also leverages structured knowledge sources such as Wikidata and tables that provide more reliable factual information. To access both unstructured and structured knowledge sources in the dynamic knowledge adapting stage, we propose an adaptive query generator that allows the generation of queries for various types of query languages, including SPARQL, SQL, and natural sentences. Moreover, to minimize error propagation between rationales, CoK corrects the rationales progressively using preceding corrected rationales to generate and correct subsequent rationales. Extensive experiments show that CoK consistently improves the performance of LLMs on knowledge-intensive tasks across different domains. In recent years, large language models (LLMs) such as ChatGPT (OpenAI, 2023) have demonstrated impressive language generation capabilities (Cheng et al., 2023; Ding et al., 2023). However, one major challenge of LLMs lies in hallucination, which is their tendency to confidently generate plausible but factually incorrect texts (Ji et al., 2023). As shown in Figure 1, given a question, "What year was the Argentine actor who directed El Tio Disparate born?" which requires factual knowledge to answer, the most advanced LLMs often provide an incorrect answer. While LLMs have the remarkable capability to recall information from their training data, effectively updating or controlling the factual knowledge within these models remains challenging (Luo et al., 2023). A promising direction to address hallucination in generation is to augment the LLMs with external knowledge (Mialon et al., 2023). These methods involve incorporating LLMs with a retrieval system, which seeks to utilize external factual knowledge to guide the generation process. Instead of relying solely on the internal training knowledge of LLMs, these methods can fetch relevant infor-Equal contribution. Xingxuan Li, Yew Ken Chia, and Bosheng Ding are under the Joint Ph.D. Program between Alibaba and their corresponding universities. We will make our code and data publicly available.