ChatGPT seems to have blindsided us all. In less than a year it has proved that it can make writers redundant, which is one of the reasons why the Writers Guild of America recently went on strike, and why a group of novelists, including Jonathan Franzen, Jodi Picoult and George RR Martin, are pursuing a lawsuit against OpenAI, the company that owns the chatbot. Imitation that appears to be original writing. From my experiments, it's obvious that ChatGPT's current level of literary sophistication is weak – it is cliche-prone and generally unconvincing – but who knows how it will develop? Writers like stretching our imaginations, coming up with ideas, working out storylines and plots, creating believable characters, overcoming creative challenges and working on a full-length piece of work over an extended period of time. Most of us write our books ourselves and while we are influenced by other writers, we're not a chatbot that has been trained on hundreds of thousands of novels for the sole purpose of mimicking human creativity. Imagine a future where those who are most adept at getting AI to write creatively will dominate, while we writers who spend a lifetime devoted to our craft are sidelined. OK, this is a worst‑case scenario, but we have to consider it, because ChatGPT and the other Large Language Models (LLMs) out there have been programmed to imagine a future that threatens many creative professions. ChatGPT is already responding to the questions I ask it in seconds, quite reliably. It is an impressive beast, but one that needs to be tamed.

Foundation language models learn from their finetuning input context in different ways. In this paper, we reformulate inputs during finetuning for challenging translation tasks, leveraging model strengths from pretraining in novel ways to improve downstream performance. These reformulations are simple data level modifications, require no additional collection of training data or modification of data at inference time. They can be applied either on single language pair translation tasks or massively multilingual translation tasks. Experiments with these techniques demonstrate significant performance improvements up to $\textbf{3.5 chrF++ on the Flores200 translation benchmark}$. We hope our research accessibly improves finetuning data efficiency, enabling more effective training to scalably improve state-of-the-art performance. Our code is released $\href{https://github.com/bri25yu/LanguageModelExperimentation}{here}.$

The integration of visual inputs with large language models (LLMs) has led to remarkable advancements in multi-modal capabilities, giving rise to visual large language models (VLLMs). However, effectively harnessing VLLMs for intricate visual perception tasks remains a challenge. In this paper, we present a novel end-to-end framework named PerceptionGPT, which efficiently and effectively equips the VLLMs with visual perception abilities by leveraging the representation power of LLMs' token embedding. Our proposed method treats the token embedding of the LLM as the carrier of spatial information, then leverage lightweight visual task encoders and decoders to perform visual perception tasks (e.g., detection, segmentation). Our approach significantly alleviates the training difficulty suffered by previous approaches that formulate the visual outputs as discrete tokens, and enables achieving superior performance with fewer trainable parameters, less training data and shorted training time. Moreover, as only one token embedding is required to decode the visual outputs, the resulting sequence length during inference is significantly reduced. Consequently, our approach enables accurate and flexible representations, seamless integration of visual perception tasks, and efficient handling of a multiple of visual outputs. We validate the effectiveness and efficiency of our approach through extensive experiments. The results demonstrate significant improvements over previous methods with much fewer trainable parameters and GPU hours, which facilitates future research in enabling LLMs with visual perception abilities.

Large language models (LLMs) such as T0, FLAN, and OPT-IML, excel in multi-tasking under a unified instruction-following paradigm, where they also exhibit remarkable generalization abilities to unseen tasks. Despite their impressive performance, these LLMs, with sizes ranging from several billion to hundreds of billions of parameters, demand substantial computational resources, making their training and inference expensive and inefficient. Furthermore, adapting these models to downstream applications, particularly complex tasks, is often unfeasible due to the extensive hardware requirements for finetuning, even when utilizing parameter-efficient approaches such as prompt tuning. Additionally, the most powerful multi-task LLMs, such as OPT-IML-175B and FLAN-PaLM-540B, are not publicly accessible, severely limiting their customization potential. To address these challenges, we introduce a pretrained small scorer, Cappy, designed to enhance the performance and efficiency of multi-task LLMs. With merely 360 million parameters, Cappy functions either independently on classification tasks or serve as an auxiliary component for LLMs, boosting their performance. Moreover, Cappy enables efficiently integrating downstream supervision without requiring LLM finetuning nor the access to their parameters. Our experiments demonstrate that, when working independently on 11 language understanding tasks from PromptSource, Cappy outperforms LLMs that are several orders of magnitude larger. Besides, on 45 complex tasks from BIG-Bench, Cappy boosts the performance of the advanced multi-task LLM, FLAN-T5, by a large margin. Furthermore, Cappy is flexible to cooperate with other LLM adaptations, including finetuning and in-context learning, offering additional performance enhancement.

Prompts have been the center of progress in advancing language models' zero-shot and few-shot performance. However, recent work finds that models can perform surprisingly well when given intentionally irrelevant or misleading prompts. Such results may be interpreted as evidence that model behavior is not "human like". In this study, we challenge a central assumption in such work: that humans would perform badly when given pathological instructions. We find that humans are able to reliably ignore irrelevant instructions and thus, like models, perform well on the underlying task despite an apparent lack of signal regarding the task they are being asked to do. However, when given deliberately misleading instructions, humans follow the instructions faithfully, whereas models do not. Our findings caution that future research should not idealize human behaviors as a monolith and should not train or evaluate models to mimic assumptions about these behaviors without first validating humans' behaviors empirically.

Large language models (LLMs) are trained on web-scale corpora that inevitably include contradictory factual information from sources of varying reliability. In this paper, we propose measuring an LLM property called trusted source alignment (TSA): the model's propensity to align with content produced by trusted publishers in the face of uncertainty or controversy. We present FactCheckQA, a TSA evaluation dataset based on a corpus of fact checking articles. We describe a simple protocol for evaluating TSA and offer a detailed analysis of design considerations including response extraction, claim contextualization, and bias in prompt formulation. Applying the protocol to PaLM-2, we find that as we scale up the model size, the model performance on FactCheckQA improves from near-random to up to 80% balanced accuracy in aligning with trusted sources.

Downstream applications often require text classification models to be accurate, robust, and interpretable. While the accuracy of the stateof-the-art language models approximates human performance, they are not designed to be interpretable and often exhibit a drop in performance on noisy data. The family of PrototypeBased Networks (PBNs) that classify examples based on their similarity to prototypical examples of a class (prototypes) is natively interpretable and shown to be robust to noise, which enabled its wide usage for computer vision tasks. In this paper, we study whether the robustness properties of PBNs transfer to text classification tasks. We design a modular and comprehensive framework for studying PBNs, which includes different backbone architectures, backbone sizes, and objective functions. Our evaluation protocol assesses the robustness of models against character-, word-, and sentence-level perturbations. Our experiments on three benchmarks show that the robustness of PBNs transfers to NLP classification tasks facing realistic perturbations. Moreover, the robustness of PBNs is supported mostly by the objective function that keeps prototypes interpretable, while the robustness superiority of PBNs over vanilla models becomes more salient as datasets get more complex.

The integration of large language models (LLMs) with social robots has emerged as a promising avenue for enhancing human-robot interactions at a time when news reports generated by artificial intelligence (AI) are gaining in credibility. This integration is expected to intensify and become a more productive resource for journalism, media, communication, and education. In this paper a novel system is proposed that integrates AI's generative pretrained transformer (GPT) model with the Pepper robot, with the aim of improving the robot's natural language understanding and response generation capabilities for enhanced social interactions. By leveraging GPT's powerful language processing capabilities, this system offers a comprehensive pipeline that incorporates voice input recording, speech-to-text transcription, context analysis, and text-to-speech synthesis action generation. The Pepper robot is enabled to comprehend user queries, generate informative responses with general knowledge, maintain contextually relevant conversations, and act as a more domain-oriented news reporter. It is also linked with a news resource and powered with a Google search capability. To evaluate the performance of the framework, experiments were conducted involving a set of diverse questions. The robot's responses were assessed on the basis of eight criteria, including relevance, context, and fluency. Despite some identified limitations, this system contributes to the field of journalism and human-robot interaction by showcasing the potential of integrating LLMs with social robots. The proposed framework opens up opportunities for improving the conversational capabilities of robots, enabling interactions that are smoother, more engaging, and more context aware.

As large language models (LLMs) impact a growing number of complex domains, it is becoming increasingly important to have fair, accurate, and rigorous evaluation benchmarks. Evaluating the reasoning skills required for business and financial NLP stands out as a particularly difficult challenge. We introduce BizBench, a new benchmark for evaluating models' ability to reason about realistic financial problems. BizBench comprises 8 quantitative reasoning tasks. Notably, BizBench targets the complex task of question-answering (QA) for structured and unstructured financial data via program synthesis (i.e., code generation). We introduce three diverse financially-themed code-generation tasks from newly collected and augmented QA data. Additionally, we isolate distinct financial reasoning capabilities required to solve these QA tasks: reading comprehension of financial text and tables, which is required to extract correct intermediate values; and understanding domain knowledge (e.g., financial formulas) needed to calculate complex solutions. Collectively, these tasks evaluate a model's financial background knowledge, ability to extract numeric entities from financial documents, and capacity to solve problems with code. We conduct an in-depth evaluation of open-source and commercial LLMs, illustrating that BizBench is a challenging benchmark for quantitative reasoning in the finance and business domain.

In this study, we investigate in-context learning (ICL) in document-level event argument extraction (EAE). The paper identifies key challenges in this problem, including example selection, context length limitation, abundance of event types, and the limitation of Chain-of-Thought (CoT) prompting in non-reasoning tasks. To address these challenges, we introduce the Heuristic-Driven Link-of-Analogy (HD-LoA) prompting method. Specifically, we hypothesize and validate that LLMs learn task-specific heuristics from demonstrations via ICL. Building upon this hypothesis, we introduce an explicit heuristic-driven demonstration construction approach, which transforms the haphazard example selection process into a methodical method that emphasizes task heuristics. Additionally, inspired by the analogical reasoning of human, we propose the link-of-analogy prompting, which enables LLMs to process new situations by drawing analogies to known situations, enhancing their adaptability. Extensive experiments show that our method outperforms the existing prompting methods and few-shot supervised learning methods, exhibiting F1 score improvements of 4.53% and 9.38% on the document-level EAE dataset. Furthermore, when applied to sentiment analysis and natural language inference tasks, the HD-LoA prompting achieves accuracy gains of 2.87% and 2.63%, indicating its effectiveness across different tasks.