Large Language Models (LLMs) are regularly being used to label data across many domains and for myriad tasks. By simply asking the LLM for an answer, or “prompting,” practitioners are able to use LLMs to quickly get a response for an arbitrary task. This prompting is done through a series of decisions by the practitioner, from simple wording of the prompt, to requesting the output in a certain data format, to jailbreaking in the case of prompts that address more sensitive topics. In this work, we ask: do variations in the way a prompt is constructed change the ultimate decision of the LLM? We answer this using a series of prompt variations across a variety of text classification tasks. We find that even the smallest of perturbations, such as adding a space at the end of a prompt, can cause the LLM to change its answer. Further, we find that requesting responses in XML and commonly used jailbreaks can have cataclysmic effects on the data labeled by LLMs.

Researchers have raised awareness about the harms of aggregating labels especially in subjective tasks that naturally contain disagreements among human annotators. In this work we show that models that are only provided aggregated labels show low confidence on high-disagreement data instances. While previous studies consider such instances as mislabeled, we argue that the reason the high-disagreement text instances have been hard-to-learn is that the conventional aggregated models underperform in extracting useful signals from subjective tasks. Inspired by recent studies demonstrating the effectiveness of learning from raw annotations, we investigate classifying using Multiple Ground Truth (Multi-GT) approaches. Our experiments show an improvement of confidence for the high-disagreement instances.

It is desirable to coarsely classify short scientific texts, such as grant or publication abstracts, for strategic insight or research portfolio management. These texts efficiently transmit dense information to experts possessing a rich body of knowledge to aid interpretation. Yet this task is remarkably difficult to automate because of brevity and the absence of context. To address this gap, we have developed a novel approach to generate and appropriately assign coarse domain-specific labels. We show that a Large Language Model (LLM) can provide metadata essential to the task, in a process akin to the augmentation of supplemental knowledge representing human intuition, and propose a workflow. As a pilot study, we use a corpus of award abstracts from the National Aeronautics and Space Administration (NASA). We develop new assessment tools in concert with established performance metrics.

Supervised classification heavily depends on datasets annotated by humans. However, in subjective tasks such as toxicity classification, these annotations often exhibit low agreement among raters. Annotations have commonly been aggregated by employing methods like majority voting to determine a single ground truth label. In subjective tasks, aggregating labels will result in biased labeling and, consequently, biased models that can overlook minority opinions. Previous studies have shed light on the pitfalls of label aggregation and have introduced a handful of practical approaches to tackle this issue. Recently proposed multi-annotator models, which predict labels individually per annotator, are vulnerable to under-determination for annotators with few samples. This problem is exacerbated in crowdsourced datasets. In this work, we propose Annotator Aware Representations for Texts (AART) for subjective classification tasks. Our approach involves learning representations of annotators, allowing for exploration of annotation behaviors. We show the improvement of our method on metrics that assess the performance on capturing individual annotators’ perspectives. Additionally, we demonstrate fairness metrics to evaluate our model’s equability of performance for marginalized annotators compared to others.

Automatic assessment of the quality of arguments has been recognized as a challenging task with significant implications for misinformation and targeted speech. While real-world arguments are tightly anchored in context, existing computational methods analyze their quality in isolation, which affects their accuracy and generalizability. We propose SPARK: a novel method for scoring argument quality based on contextualization via relevant knowledge. We devise four augmentations that leverage large language models to provide feedback, infer hidden assumptions, supply a similar-quality argument, or give a counter-argument. SPARK uses a dual-encoder Transformer architecture to enable the original argument and its augmentation to be considered jointly. Our experiments in both in-domain and zero-shot setups show that SPARK consistently outperforms existing techniques across multiple metrics

The propagation of offensive content through social media channels has garnered attention of the research community. Multiple works have proposed various semantically related yet subtle distinct categories of offensive speech. In this work, we explore meta-learning approaches to leverage the diversity of offensive speech corpora to enhance their reliable and efficient detection. We propose a joint embedding architecture that incorporates the input’s label and definition for classification via Prototypical Network. Our model achieves at least 75% of the maximal F1-score while using less than 10% of the available training data across 4 datasets. Our experimental findings also provide a case study of training strategies valuable to combat resource scarcity.

We present a causal language analysis pipeline that leverages a Large Language Model to identify causal claims made in natural language documents, and aggregates claims across a corpus to produce a causal claim network. The pipeline then applies a clustering algorithm that groups causal claims based on their semantic topics. We demonstrate the pipeline by modeling causal belief systems surrounding the Covid-19 vaccine from tweets.

Pragmatic reference enables efficient interpersonal communication. Prior work uses simple reference games to test models of pragmatic reasoning, often with unidentified speakers and listeners. In practice, however, speakers’ sociocultural background shapes their pragmatic assumptions. For example, readers of this paper assume NLP refers to Natural Language Processing, and not “Neuro-linguistic Programming.” This work introduces the Cultural Codes dataset, which operationalizes sociocultural pragmatic inference in a simple word reference game. Cultural Codes is based on the multi-turn collaborative two-player game, Codenames Duet. Our dataset consists of 794 games with 7,703 turns, distributed across 153 unique players. Alongside gameplay, we collect information about players’ personalities, values, and demographics. Utilizing theories of communication and pragmatics, we predict each player’s actions via joint modeling of their sociocultural priors and the game context. Our experiments show that accounting for background characteristics significantly improves model performance for tasks related to both clue-giving and guessing, indicating that sociocultural priors play a vital role in gameplay decisions.

Deep neural models for named entity recognition (NER) have shown impressive results in overcoming label scarcity and generalizing to unseen entities by leveraging distant supervision and auxiliary information such as explanations. However, the costs of acquiring such additional information are generally prohibitive. In this paper, we present a novel two-stage framework (AutoTriggER) to improve NER performance by automatically generating and leveraging “entity triggers” which are human-readable cues in the text that help guide the model to make better decisions. Our framework leverages post-hoc explanation to generate rationales and strengthens a model’s prior knowledge using an embedding interpolation technique. This approach allows models to exploit triggers to infer entity boundaries and types instead of solely memorizing the entity words themselves. Through experiments on three well-studied NER datasets, AutoTriggER shows strong label-efficiency, is capable of generalizing to unseen entities, and outperforms the RoBERTa-CRF baseline by nearly 0.5 F1 points on average.

Temporal knowledge graph (TKG) forecasting benchmarks challenge models to predict future facts using knowledge of past facts. In this paper, we develop an approach to use in-context learning (ICL) with large language models (LLMs) for TKG forecasting. Our extensive evaluation compares diverse baselines, including both simple heuristics and state-of-the-art (SOTA) supervised models, against pre-trained LLMs across several popular benchmarks and experimental settings. We observe that naive LLMs perform on par with SOTA models, which employ carefully designed architectures and supervised training for the forecasting task, falling within the (-3.6%, +1.5%) Hits@1 margin relative to the median performance. To better understand the strengths of LLMs for forecasting, we explore different approaches for selecting historical facts, constructing prompts, controlling information propagation, and parsing outputs into a probability distribution. A surprising finding from our experiments is that LLM performance endures (±0.4% Hit@1) even when semantic information is removed by mapping entities/relations to arbitrary numbers, suggesting that prior semantic knowledge is unnecessary; rather, LLMs can leverage the symbolic patterns in the context to achieve such a strong performance. Our analysis also reveals that ICL enables LLMs to learn irregular patterns from the historical context, going beyond frequency and recency biases

Warning: this paper contains content that maybe offensive or upsetting. Recent research in Natural Language Processing (NLP) has advanced the development of various toxicity detection models with the intention of identifying and mitigating toxic language from existing systems. Despite the abundance of research in this area, less attention has been given to adversarial attacks that force the system to generate toxic language and the defense against them. Existing work to generate such attacks is either based on human-generated attacks which is costly and not scalable or, in case of automatic attacks, the attack vector does not conform to human-like language, which can be detected using a language model loss. In this work, we propose attacks against conversational agents that are imperceptible, i.e., they fit the conversation in terms of coherency, relevancy, and fluency, while they are effective and scalable, i.e., they can automatically trigger the system into generating toxic language. We then propose a defense mechanism against such attacks which not only mitigates the attack but also attempts to maintain the conversational flow. Through automatic and human evaluations, we show that our defense is effective at avoiding toxic language generation even against imperceptible toxicity triggers while the generated language fits the conversation in terms of coherency and relevancy. Lastly, we establish the generalizability of such a defense mechanism on language generation models beyond conversational agents.

The widespread use of Artificial Intelligence (AI) in consequential domains, such as health-care and parole decision-making systems, has drawn intense scrutiny on the fairness of these methods. However, ensuring fairness is often insufficient as the rationale for a contentious decision needs to be audited, understood, and defended. We propose that the attention mechanism can be used to ensure fair outcomes while simultaneously providing feature attributions to account for how a decision was made. Toward this goal, we design an attention-based model that can be leveraged as an attribution framework. It can identify features responsible for both performance and fairness of the model through attention interventions and attention weight manipulation. Using this attribution framework, we then design a post-processing bias mitigation strategy and compare it with a suite of baselines. We demonstrate the versatility of our approach by conducting experiments on two distinct data types, tabular and textual.

Warning: this paper contains content that may be offensive or upsetting. Commonsense knowledge bases (CSKB) are increasingly used for various natural language processing tasks. Since CSKBs are mostly human-generated and may reflect societal biases, it is important to ensure that such biases are not conflated with the notion of commonsense. Here we focus on two widely used CSKBs, ConceptNet and GenericsKB, and establish the presence of bias in the form of two types of representational harms, overgeneralization of polarized perceptions and representation disparity across different demographic groups in both CSKBs. Next, we find similar representational harms for downstream models that use ConceptNet. Finally, we propose a filtering-based approach for mitigating such harms, and observe that our filtered-based approach can reduce the issues in both resources and models but leads to a performance drop, leaving room for future work to build fairer and stronger commonsense models.

Event forecasting is a challenging, yet important task, as humans seek to constantly plan for the future. Existing automated forecasting studies rely mostly on structured data, such as time-series or event-based knowledge graphs, to help predict future events. In this work, we aim to formulate a task, construct a dataset, and provide benchmarks for developing methods for event forecasting with large volumes of unstructured text data. To simulate the forecasting scenario on temporal news documents, we formulate the problem as a restricted-domain, multiple-choice, question-answering (QA) task. Unlike existing QA tasks, our task limits accessible information, and thus a model has to make a forecasting judgement. To showcase the usefulness of this task formulation, we introduce ForecastQA, a question-answering dataset consisting of 10,392 event forecasting questions, which have been collected and verified via crowdsourcing efforts. We present our experiments on ForecastQA using BERTbased models and find that our best model achieves 61.0% accuracy on the dataset, which still lags behind human performance by about 19%. We hope ForecastQA will support future research efforts in bridging this gap.

Discrepancies exist among different cultures or languages. A lack of mutual understanding among different colingual groups about the perspectives on specific values or events may lead to uninformed decisions or biased opinions. Thus, automatically understanding the group perspectives can provide essential back-ground for many natural language processing tasks. In this paper, we study colingual groups and use language corpora as a proxy to identify their distributional perspectives. We present a novel computational approach to learn shared understandings, and benchmark our method by building culturally-aware models for the English, Chinese, and Japanese languages. Ona held out set of diverse topics, including marriage, corruption, democracy, etc., our model achieves high correlation with human judgements regarding intra-group values and inter-group differences