Natural Language Processing (NLP) research is increasingly focusing on the use of Large Language Models (LLMs), with some of the most popular ones being either fully or partially closed-source. The lack of access to model details, especially regarding training data, has repeatedly raised concerns about data contamination among researchers. Several attempts have been made to address this issue, but they are limited to anecdotal evidence and trial and error. Additionally, they overlook the problem of indirect data leaking, where modelsare iteratively improved by using data coming from users. In this work, we conduct the first systematic analysis of work using OpenAI’s GPT-3.5 and GPT-4, the most prominently used LLMs today, in the context of data contamination. By analysing 255 papers and considering OpenAI’s data usage policy, we extensively document the amount of data leaked to these models during the first year after the model’s release. We report that these models have been globally exposed to ∼4.7M samples from 263 benchmarks. At the same time, we document a number of evaluation malpractices emerging in the reviewed papers, such as unfair or missing baseline comparisons and reproducibility issues. We release our results as a collaborative project on https://leak-llm.github.io/, where other researchers can contribute to our efforts.

Hallucination of text ungrounded in the input is a well-known problem in neural data-to-text generation. Many methods have been proposed to mitigate it, but they typically require altering model architecture or collecting additional data, and thus cannot be easily applied to an existing model. In this paper, we explore a new way to mitigate hallucinations by combining the probabilistic output of a generator language model (LM) with the output of a special “text critic” classifier, which guides the generation by assessing the match between the input data and the text generated so far. Our method does not need any changes to the underlying LM’s architecture or training procedure and can thus be combined with any model and decoding operating on word probabilities. The critic does not need any additional training data, using the base LM’s training data and synthetic negative examples. Our experimental results show that our method improves over the baseline on the WebNLG and OpenDialKG benchmarks.

Clickbait posts are a widespread problem in the webspace. The generation of spoilers, i.e. short texts that neutralize clickbait by providing information that makes it uninteresting, is one of the proposed solutions to the problem. Current state-of-the-art methods are based on passage retrieval or question answering approaches and are limited to generating spoilers only in the form of a phrase or a passage. In this work, we propose an ensemble of fine-tuned large language models for clickbait spoiler generation. Our approach is not limited to phrase or passage spoilers, but is also able to generate multipart spoilers that refer to several non-consecutive parts of text. Experimental evaluation demonstrates that the proposed ensemble model outperforms the baselines in terms of BLEU, METEOR and BERTScore metrics.

This work presents our efforts to reproduce the results of the human evaluation experiment presented in the paper of Vamvas and Sennrich (2022), which evaluated an automatic system detecting over- and undertranslations (translations containing more or less information than the original) in machine translation (MT) outputs. Despite the high quality of the documentation and code provided by the authors, we discuss some problems we found in reproducing the exact experimental setup and offer recommendations for improving reproducibility. Our replicated results generally confirm the conclusions of the original study, but in some cases statistically significant differences were observed, suggesting a high variability of human annotation.

Clickbait posts are a common problem on social media platforms, as they often deceive users by providing misleading or sensational headlines that do not match the content of the linked web page. The aim of this study is to create a technique for identifying the specific type of suitable spoiler - be it a phrase, a passage, or a multipart spoiler - needed to neutralize clickbait posts. This is achieved by developing a machine learning classifier analyzing both the clickbait post and the linked web page. Modern approaches for constructing a text classifier usually rely on fine-tuning a transformer-based model pre-trained on large unsupervised corpora. However, recent advances in the development of large-scale language models have led to the emergence of a new transfer learning paradigm based on prompt engineering. In this work, we study these two transfer learning techniques and compare their effectiveness for clickbait spoiler-type detection task. Our experimental results show that for this task, using the standard fine-tuning method gives better results than using prompting. The best model can achieve a similar performance to that presented by Hagen et al. (2022).

This paper describes the systems submitted by team6 for ChatEval, the DSTC 11 Track 4 competition. We present three different approaches to predicting turn-level qualities of chatbot responses based on large language models (LLMs). We report improvement over the baseline using dynamic few-shot examples from a vector store for the prompts for ChatGPT. We also analyze the performance of the other two approaches and report needed improvements for future work. We developed the three systems over just two weeks, showing the potential of LLMs for this task. An ablation study conducted after the challenge deadline shows that the new Llama 2 models are closing the performance gap between ChatGPT and open-source LLMs. However, we find that the Llama 2 models do not benefit from few-shot examples in the same way as ChatGPT.

In this work, we study the unsupervised cross-lingual word embeddings mapping method presented by Artetxe et al. (2018). First, wesuccessfully reproduced the experiments performed in the original work, finding only minor differences. Furthermore, we verified themethod’s robustness on different embedding representations and new language pairs, particularly these involving Slavic languages likePolish or Czech. We also performed an experimental analysis of the impact of the method’s parameters on the final result. Finally, welooked for an alternative way of initialization, which directly relies on the isometric assumption. Our work confirms the results presentedearlier, at the same time pointing at interesting problems occurring while using the method with different types of embeddings or onless-common language pairs.