Existing research on Domain Robustness (DR) suffers from disparate setups, limited task variety, and scarce research on recent capabilities such as in-context learning. Furthermore, the common practice of measuring DR might not be fully accurate. Current research focuses on challenge sets and relies solely on the Source Drop (SD): Using the source in-domain performance as a reference point for degradation. However, we argue that the Target Drop (TD), which measures degradation from the target in-domain performance, should be used as a complementary point of view. To address these issues, we first curated a DR benchmark comprised of 7 diverse NLP tasks, which enabled us to measure both the SD and the TD. We then conducted a comprehensive large-scale DR study involving over 14,000 domain shifts across 21 fine-tuned models and few-shot LLMs. We found that both model types suffer from drops upon domain shifts. While fine-tuned models excel in-domain, few-shot LLMs often surpass them cross-domain, showing better robustness. In addition, we found that a large SD can often be explained by shifting to a harder domain rather than by a genuine DR challenge, and this highlights the importance of TD as a complementary metric. We hope our study will shed light on the current DR state of NLP models and promote improved evaluation practices toward more robust models.
Most work on modeling the conversation history in Conversational Question Answering (CQA) reports a single main result on a common CQA benchmark. While existing models show impressive results on CQA leaderboards, it remains unclear whether they are robust to shifts in setting (sometimes to more realistic ones), training data size (e.g., from large to small sets) and domain. In this work, we design and conduct the first large-scale robustness study of history modeling approaches for CQA. We find that high benchmark scores do not necessarily translate to strong robustness, and that various methods can perform extremely differently under different settings. Equipped with the insights from our study, we design a novel prompt-based history modeling approach and demonstrate its strong robustness across various settings. Our approach is inspired by existing methods that highlight historic answers in the passage. However, instead of highlighting by modifying the passage token embeddings, we add textual prompts directly in the passage text. Our approach is simple, easy to plug into practically any model, and highly effective, thus we recommend it as a starting point for future model developers. We also hope that our study and insights will raise awareness to the importance of robustness-focused evaluation, in addition to obtaining high leaderboard scores, leading to better CQA systems.1
Natural Language Processing algorithms have made incredible progress, but they still struggle when applied to out-of-distribution examples. We address a challenging and underexplored version of this domain adaptation problem, where an algorithm is trained on several source domains, and then applied to examples from unseen domains that are unknown at training time. Particularly, no examples, labeled or unlabeled, or any other knowledge about the target domain are available to the algorithm at training time. We present PADA: An example-based autoregressive Prompt learning algorithm for on-the-fly Any-Domain Adaptation, based on the T5 language model. Given a test example, PADA first generates a unique prompt for it and then, conditioned on this prompt, labels the example with respect to the NLP prediction task. PADA is trained to generate a prompt that is a token sequence of unrestricted length, consisting of Domain Related Features (DRFs) that characterize each of the source domains. Intuitively, the generated prompt is a unique signature that maps the test example to a semantic space spanned by the source domains. In experiments with 3 tasks (text classification and sequence tagging), for a total of 14 multi-source adaptation scenarios, PADA substantially outperforms strong baselines.1
The product reviews summarization task aims to automatically produce a short summary for a set of reviews of a given product. Such summaries are expected to aggregate a range of different opinions in a concise, coherent and informative manner. This challenging task gives rise to two shortcomings in existing work. First, summarizers tend to favor generic content that appears in reviews for many different products, resulting in template-like, less informative summaries. Second, as reviewers often disagree on the pros and cons of a given product, summarizers sometimes yield inconsistent, self-contradicting summaries. We propose the PASS system (Perturb-and-Select Summarizer) that employs a large pre-trained Transformer-based model (T5 in our case), which follows a few-shot fine-tuning scheme. A key component of the PASS system relies on applying systematic perturbations to the model’s input during inference, which allows it to generate multiple different summaries per product. We develop a method for ranking these summaries according to desired criteria, coherence in our case, enabling our system to almost entirely avoid the problem of self-contradiction. We compare our system against strong baselines on publicly available datasets, and show that it produces summaries which are more informative, diverse and coherent.
Understanding predictions made by deep neural networks is notoriously difficult, but also crucial to their dissemination. As all machine learning–based methods, they are as good as their training data, and can also capture unwanted biases. While there are tools that can help understand whether such biases exist, they do not distinguish between correlation and causation, and might be ill-suited for text-based models and for reasoning about high-level language concepts. A key problem of estimating the causal effect of a concept of interest on a given model is that this estimation requires the generation of counterfactual examples, which is challenging with existing generation technology. To bridge that gap, we propose CausaLM, a framework for producing causal model explanations using counterfactual language representation models. Our approach is based on fine-tuning of deep contextualized embedding models with auxiliary adversarial tasks derived from the causal graph of the problem. Concretely, we show that by carefully choosing auxiliary adversarial pre-training tasks, language representation models such as BERT can effectively learn a counterfactual representation for a given concept of interest, and be used to estimate its true causal effect on model performance. A byproduct of our method is a language representation model that is unaffected by the tested concept, which can be useful in mitigating unwanted bias ingrained in the data.1
Sports competitions are widely researched in computer and social science, with the goal of understanding how players act under uncertainty. Although there is an abundance of computational work on player metrics prediction based on past performance, very few attempts to incorporate out-of-game signals have been made. Specifically, it was previously unclear whether linguistic signals gathered from players’ interviews can add information that does not appear in performance metrics. To bridge that gap, we define text classification tasks of predicting deviations from mean in NBA players’ in-game actions, which are associated with strategic choices, player behavior, and risk, using their choice of language prior to the game. We collected a data set of transcripts from key NBA players’ pre-game interviews and their in-game performance metrics, totalling 5,226 interview-metric pairs. We design neural models for players’ action prediction based on increasingly more complex aspects of the language signals in their open-ended interviews. Our models can make their predictions based on the textual signal alone, or on a combination of that signal with signals from past-performance metrics. Our text-based models outperform strong baselines trained on performance metrics only, demonstrating the importance of language usage for action prediction. Moreover, the models that utilize both textual input and past-performance metrics produced the best results. Finally, as neural networks are notoriously difficult to interpret, we propose a method for gaining further insight into what our models have learned. Particularly, we present a latent Dirichlet allocation–based analysis, where we interpret model predictions in terms of correlated topics. We find that our best performing textual model is most associated with topics that are intuitively related to each prediction task and that better models yield higher correlation with more informative topics.1