In this work, we carry out a data archaeology to infer books that are known to ChatGPT and GPT-4 using a name cloze membership inference query. We find that OpenAI models have memorized a wide collection of copyrighted materials, and that the degree of memorization is tied to the frequency with which passages of those books appear on the web. The ability of these models to memorize an unknown set of books complicates assessments of measurement validity for cultural analytics by contaminating test data; we show that models perform much better on memorized books than on non-memorized books for downstream tasks. We argue that this supports a case for open models whose training data is known.

Ambiguity is an intrinsic feature of natural language. Managing ambiguity is a key part of human language understanding, allowing us to anticipate misunderstanding as communicators and revise our interpretations as listeners. As language models (LMs) are increasingly employed as dialogue interfaces and writing aids, handling ambiguous language is critical to their success. We characterize ambiguity in a sentence by its effect on entailment relations with another sentence, and collect AmbiEnt, a linguist-annotated benchmark of 1,645 examples with diverse kinds of ambiguity. We design a suite of tests based on AmbiEnt, presenting the first evaluation of pretrained LMs to recognize ambiguity and disentangle possible meanings. We find that the task remains extremely challenging, including for GPT-4, whose generated disambiguations are considered correct only 32% of the time in human evaluation, compared to 90% for disambiguations in our dataset. Finally, to illustrate the value of ambiguity-sensitive tools, we show that a multilabel NLI model can flag political claims in the wild that are misleading due to ambiguity. We encourage the field to rediscover the importance of ambiguity for NLP.

ChatGPT shows remarkable capabilities for machine translation (MT). Several prior studies have shown that it achieves comparable results to commercial systems for high-resource languages, but lags behind in complex tasks, e.g., low-resource and distant-language-pairs translation. However, they usually adopt simple prompts which can not fully elicit the capability of ChatGPT. In this paper, we aim to further mine ChatGPT's translation ability by revisiting several aspects: temperature, task information, and domain information, and correspondingly propose an optimal temperature setting and two (simple but effective) prompts: Task-Specific Prompts (TSP) and Domain-Specific Prompts (DSP). We show that: 1) The performance of ChatGPT depends largely on temperature, and a lower temperature usually can achieve better performance; 2) Emphasizing the task information can further improve ChatGPT's performance, particularly in complex MT tasks; 3) Introducing domain information can elicit ChatGPT's generalization ability and improve its performance in the specific domain; 4) ChatGPT tends to generate hallucinations for non-English-centric MT tasks, which can be partially addressed by our proposed prompts but still need to be highlighted for the MT/NLP community. We also explore the effects of advanced in-context learning strategies and find a (negative but interesting) observation: the powerful chain-of-thought prompt leads to word-by-word translation behavior, thus bringing significant translation degradation.

The task of repository-level code completion is to continue writing the unfinished code based on a broader context of the repository. While for automated code completion tools, it is difficult to utilize the useful information scattered in different files. We propose RepoCoder, a simple, generic, and effective framework to address the challenge. It streamlines the repository-level code completion process by incorporating a similarity-based retriever and a pre-trained code language model in an iterative retrieval-generation pipeline. RepoCoder makes effective utilization of repository-level information for code completion and has the ability to generate code at various levels of granularity. Moreover, we propose a new benchmark RepoEval, which consists of the latest and high-quality real-world repositories covering line, API invocation, and function body completion scenarios. Experimental results indicate that RepoCoder significantly improves the In-File completion baseline by over 10% in all settings and consistently outperforms the vanilla retrieval-augmented code completion approach. Furthermore, we validate the effectiveness of RepoCoder through comprehensive analysis, providing valuable insights for future research. Our source code and benchmark are publicly available: https://github.com/microsoft/CodeT/tree/main/RepoCoder

A rapidly increasing amount of human conversation occurs online. But divisiveness and conflict can fester in text-based interactions on social media platforms, in messaging apps, and on other digital forums. Such toxicity increases polarization and, importantly, corrodes the capacity of diverse societies to develop efficient solutions to complex social problems that impact everyone. Scholars and civil society groups promote interventions that can make interpersonal conversations less divisive or more productive in offline settings, but scaling these efforts to the amount of discourse that occurs online is extremely challenging. We present results of a large-scale experiment that demonstrates how online conversations about divisive topics can be improved with artificial intelligence tools. Specifically, we employ a large language model to make real-time, evidence-based recommendations intended to improve participants' perception of feeling understood in conversations. We find that these interventions improve the reported quality of the conversation, reduce political divisiveness, and improve the tone, without systematically changing the content of the conversation or moving people's policy attitudes. These findings have important implications for future research on social media, political deliberation, and the growing community of scholars interested in the place of artificial intelligence within computational social science.

Machine-Generated Text (MGT) detection, a task that discriminates MGT from Human-Written Text (HWT), plays a crucial role in preventing misuse of text generative models, which excel in mimicking human writing style recently. Latest proposed detectors usually take coarse text sequences as input and fine-tune pretrained models with standard cross-entropy loss. However, these methods fail to consider the linguistic structure of texts. Moreover, they lack the ability to handle the low-resource problem which could often happen in practice considering the enormous amount of textual data online. In this paper, we present a coherence-based contrastive learning model named CoCo to detect the possible MGT under low-resource scenario. To exploit the linguistic feature, we encode coherence information in form of graph into text representation. To tackle the challenges of low data resource, we employ a contrastive learning framework and propose an improved contrastive loss for preventing performance degradation brought by simple samples. The experiment results on two public datasets and two self-constructed datasets prove our approach outperforms the state-of-art methods significantly. Also, we surprisingly find that MGTs originated from up-to-date language models could be easier to detect than these from previous models, in our experiments. And we propose some preliminary explanations for this counter-intuitive phenomena. All the codes and datasets are open-sourced.

As information extraction (IE) systems have grown more adept at processing whole documents, the classic task of template filling has seen renewed interest as benchmark for document-level IE. In this position paper, we call into question the suitability of template filling for this purpose. We argue that the task demands definitive answers to thorny questions of event individuation -- the problem of distinguishing distinct events -- about which even human experts disagree. Through an annotation study and error analysis, we show that this raises concerns about the usefulness of template filling metrics, the quality of datasets for the task, and the ability of models to learn it. Finally, we consider possible solutions.

Many real-world tasks involve a mixed-initiative setup, wherein humans and AI systems collaboratively perform a task. While significant work has been conducted towards enabling humans to specify, through language, exactly how an agent should complete a task (i.e., low-level specification), prior work lacks on interpreting the high-level strategic intent of the human commanders. Parsing strategic intent from language will allow autonomous systems to independently operate according to the user's plan without frequent guidance or instruction. In this paper, we build a computational interface capable of translating unstructured language strategies into actionable intent in the form of goals and constraints. Leveraging a game environment, we collect a dataset of over 1000 examples, mapping language strategies to the corresponding goals and constraints, and show that our model, trained on this dataset, significantly outperforms human interpreters in inferring strategic intent (i.e., goals and constraints) from language (p < 0.05). Furthermore, we show that our model (125M parameters) significantly outperforms ChatGPT for this task (p < 0.05) in a low-data setting.

When OpenAI published details of the stunningly capable AI language model GPT-4, which powers ChatGPT, in March, its researchers filled 100 pages. They also left out a few important details--like anything substantial about how it was actually built or how it works. That was no accidental oversight, of course. OpenAI and other big companies are keen to keep the workings of their most prized algorithms shrouded in mystery, in part out of fear the technology might be misused but also from worries about giving competitors a leg up. A study released by researchers at Stanford University this week shows just how deep--and potentially dangerous--the secrecy is around GPT-4 and other cutting-edge AI systems.

The reason Intel is partnering with more than 100 software developers on more than 300 AI-accelerated features is a simple one: Intel has introduced AI capabilities inside of its 14th-gen "Meteor Lake" Core Ultra chips for laptops, and it needs them to do, well, something. AI has become synonymous with Bing Chat, Google Bard, Windows Copilot, and ChatGPT -- all AI tools that live in the cloud. Intel's new AI Acceleration Program, launching in anticipation of Meter Lake's official launch on Dec. 14, will try to convince consumers that AI should run locally on their PCs. That may be a tough sell to consumers, who may not know -- or care -- where these functions are being processed. Intel, though, desperately does -- and has tried to get this message across at its Intel Innovation conference, earnings reports, and more.