Regular-pattern-sensitive CRFs for Distant Label Interactions

Linear-chain conditional random fields (CRFs) are a common model component for sequence labeling tasks when modeling the interactions between different labels is important. However, the Markov assumption limits linear-chain CRFs to only directly modeling interactions between adjacent labels. Weighted finite-state transducers (FSTs) are a related approach which can be made to model distant label-label interactions, but exact label inference is intractable for these models in the general case, and the task of selecting an appropriate automaton structure for the desired interaction types poses a practical challenge. In this work, we present regular-pattern-sensitive CRFs (RPCRFs), a method of enriching standard linear-chain CRFs with the ability to learn long-distance label interactions which occur in user-specified patterns. This approach allows users to write regular-expression label patterns concisely specifying which types of interactions the model should take into account, allowing the model to learn from data whether and in which contexts these patterns occur. The result can be interpreted alternatively as a CRF augmented with additional, non-local potentials, or as a finite-state transducer whose structure is defined by a set of easily-interpretable patterns. Critically, unlike the general case for FSTs (and for non-chain CRFs), exact training and inference are tractable for many pattern sets. In this work, we detail how a RPCRF can be automatically constructed from a set of user-specified patterns, and demonstrate the model's effectiveness on synthetic data, showing how different types of patterns can capture different nonlocal dependency structures in label sequences.

Which Demographics do LLMs Default to During Annotation?

Demographics and cultural background of annotators influence the labels they assign in text annotation -- for instance, an elderly woman might find it offensive to read a message addressed to a "bro", but a male teenager might find it appropriate. It is therefore important to acknowledge label variations to not under-represent members of a society. Two research directions developed out of this observation in the context of using large language models (LLM) for data annotations, namely (1) studying biases and inherent knowledge of LLMs and (2) injecting diversity in the output by manipulating the prompt with demographic information. We combine these two strands of research and ask the question to which demographics an LLM resorts to when no demographics is given. To answer this question, we evaluate which attributes of human annotators LLMs inherently mimic. Furthermore, we compare non-demographic conditioned prompts and placebo-conditioned prompts (e.g., "you are an annotator who lives in house number 5") to demographics-conditioned prompts ("You are a 45 year old man and an expert on politeness annotation. How do you rate {instance}"). We study these questions for politeness and offensiveness annotations on the POPQUORN data set, a corpus created in a controlled manner to investigate human label variations based on demographics which has not been used for LLM-based analyses so far. We observe notable influences related to gender, race, and age in demographic prompting, which contrasts with previous studies that found no such effects.

How Entangled is Factuality and Deception in German?

The statement "The earth is flat" is factually inaccurate, but if someone truly believes and argues in its favor, it is not deceptive. Research on deception detection and fact checking often conflates factual accuracy with the truthfulness of statements. This assumption makes it difficult to (a) study subtle distinctions and interactions between the two and (b) gauge their effects on downstream tasks. The belief-based deception framework disentangles these properties by defining texts as deceptive when there is a mismatch between what people say and what they truly believe. In this study, we assess if presumed patterns of deception generalize to German language texts. We test the effectiveness of computational models in detecting deception using an established corpus of belief-based argumentation. Finally, we gauge the impact of deception on the downstream task of fact checking and explore if this property confounds verification models. Surprisingly, our analysis finds no correlation with established cues of deception. Previous work claimed that computational models can outperform humans in deception detection accuracy, however, our experiments show that both traditional and state-of-the-art models struggle with the task, performing no better than random guessing. For fact checking, we find that Natural Language Inference-based verification performs worse on non-factual and deceptive content, while prompting Large Language Models for the same task is less sensitive to these properties.

Prompt-based Personality Profiling: Reinforcement Learning for Relevance Filtering

Author profiling is the task of inferring characteristics about individuals by analyzing content they share. Supervised machine learning still dominates automatic systems that perform this task, despite the popularity of prompting large language models to address natural language understanding tasks. One reason is that the classification instances consist of large amounts of posts, potentially a whole user profile, which may exceed the input length of Transformers. Even if a model can use a large context window, the entirety of posts makes the application of API-accessed black box systems costly and slow, next to issues which come with such "needle-in-the-haystack" tasks. To mitigate this limitation, we propose a new method for author profiling which aims at distinguishing relevant from irrelevant content first, followed by the actual user profiling only with relevant data. To circumvent the need for relevance-annotated data, we optimize this relevance filter via reinforcement learning with a reward function that utilizes the zero-shot capabilities of large language models. We evaluate our method for Big Five personality trait prediction on two Twitter corpora. On publicly available real-world data with a skewed label distribution, our method shows similar efficacy to using all posts in a user profile, but with a substantially shorter context. An evaluation on a version of these data balanced with artificial posts shows that the filtering to relevant posts leads to a significantly improved accuracy of the predictions.

Entity-Level Sentiment: More than the Sum of Its Parts

In sentiment analysis of longer texts, there may be a variety of topics discussed, of entities mentioned, and of sentiments expressed regarding each entity. We find a lack of studies exploring how such texts express their sentiment towards each entity of interest, and how these sentiments can be modelled. In order to better understand how sentiment regarding persons and organizations (each entity in our scope) is expressed in longer texts, we have collected a dataset of expert annotations where the overall sentiment regarding each entity is identified, together with the sentence-level sentiment for these entities separately. We show that the reader's perceived sentiment regarding an entity often differs from an arithmetic aggregation of sentiments at the sentence level. Only 70\% of the positive and 55\% of the negative entities receive a correct overall sentiment label when we aggregate the (human-annotated) sentiment labels for the sentences where the entity is mentioned. Our dataset reveals the complexity of entity-specific sentiment in longer texts, and allows for more precise modelling and evaluation of such sentiment expressions.

"You are an expert annotator": Automatic Best-Worst-Scaling Annotations for Emotion Intensity Modeling

Labeling corpora constitutes a bottleneck to create models for new tasks or domains. Large language models mitigate the issue with automatic corpus labeling methods, particularly for categorical annotations. Some NLP tasks such as emotion intensity prediction, however, require text regression, but there is no work on automating annotations for continuous label assignments. Regression is considered more challenging than classification: The fact that humans perform worse when tasked to choose values from a rating scale lead to comparative annotation methods, including best-worst scaling. This raises the question if large language model-based annotation methods show similar patterns, namely that they perform worse on rating scale annotation tasks than on comparative annotation tasks. To study this, we automate emotion intensity predictions and compare direct rating scale predictions, pairwise comparisons and best-worst scaling. We find that the latter shows the highest reliability. A transformer regressor fine-tuned on these data performs nearly on par with a model trained on the original manual annotations.

Can Factual Statements be Deceptive? The DeFaBel Corpus of Belief-based Deception

If a person firmly believes in a non-factual statement, such as "The Earth is flat", and argues in its favor, there is no inherent intention to deceive. As the argumentation stems from genuine belief, it may be unlikely to exhibit the linguistic properties associated with deception or lying. This interplay of factuality, personal belief, and intent to deceive remains an understudied area. Disentangling the influence of these variables in argumentation is crucial to gain a better understanding of the linguistic properties attributed to each of them. To study the relation between deception and factuality, based on belief, we present the DeFaBel corpus, a crowd-sourced resource of belief-based deception. To create this corpus, we devise a study in which participants are instructed to write arguments supporting statements like "eating watermelon seeds can cause indigestion", regardless of its factual accuracy or their personal beliefs about the statement. In addition to the generation task, we ask them to disclose their belief about the statement. The collected instances are labelled as deceptive if the arguments are in contradiction to the participants' personal beliefs. Each instance in the corpus is thus annotated (or implicitly labelled) with personal beliefs of the author, factuality of the statement, and the intended deceptiveness. The DeFaBel corpus contains 1031 texts in German, out of which 643 are deceptive and 388 are non-deceptive. It is the first publicly available corpus for studying deception in German. In our analysis, we find that people are more confident in the persuasiveness of their arguments when the statement is aligned with their belief, but surprisingly less confident when they are generating arguments in favor of facts. The DeFaBel corpus can be obtained from https://www.ims.uni-stuttgart.de/data/defabel

Understanding Fine-grained Distortions in Reports of Scientific Findings

Distorted science communication harms individuals and society as it can lead to unhealthy behavior change and decrease trust in scientific institutions. Given the rapidly increasing volume of science communication in recent years, a fine-grained understanding of how findings from scientific publications are reported to the general public, and methods to detect distortions from the original work automatically, are crucial. Prior work focused on individual aspects of distortions or worked with unpaired data. In this work, we make three foundational contributions towards addressing this problem: (1) annotating 1,600 instances of scientific findings from academic papers paired with corresponding findings as reported in news articles and tweets wrt. four characteristics: causality, certainty, generality and sensationalism; (2) establishing baselines for automatically detecting these characteristics; and (3) analyzing the prevalence of changes in these characteristics in both human-annotated and large-scale unlabeled data. Our results show that scientific findings frequently undergo subtle distortions when reported. Tweets distort findings more often than science news reports. Detecting fine-grained distortions automatically poses a challenging task. In our experiments, fine-tuned task-specific models consistently outperform few-shot LLM prompting.

English Prompts are Better for NLI-based Zero-Shot Emotion Classification than Target-Language Prompts

Emotion classification in text is a challenging and subjective task, due to the involved cognitive inference processes that are required to interpret a textual stimulus. In addition, the set of emotion categories is highly domain-specific. For instance, literature analysis might require the use of aesthetic emotions (e.g., finding something beautiful), and social media analysis could benefit from fine-grained sets (e.g., separating anger from annoyance) in contrast to basic emotion categories. This renders the task an interesting field for zero-shot classifications, in which the label set is not known at model development time. Unfortunately, most resources for emotion analysis are English, and therefore, most studies on emotion analysis have been performed in English, including those that involve prompting language models for text labels. This leaves us with a research gap that we address in this paper: In which language should we prompt for emotion labels on non-English texts? This is particularly of interest when we have access to a multilingual large language model, because we could request labels with English prompts even for non-English data. Our experiments with natural language inference-based language models show that it is consistently better to use English prompts even if the data is in a different language.

What Makes Medical Claims (Un)Verifiable? Analyzing Entity and Relation Properties for Fact Verification

Biomedical claim verification fails if no evidence can be discovered. In these cases, the fact-checking verdict remains unknown and the claim is unverifiable. To improve upon this, we have to understand if there are any claim properties that impact its verifiability. In this work we assume that entities and relations define the core variables in a biomedical claim's anatomy and analyze if their properties help us to differentiate verifiable from unverifiable claims. In a study with trained annotation experts we prompt them to find evidence for biomedical claims, and observe how they refine search queries for their evidence search. This leads to the first corpus for scientific fact verification annotated with subject-relation-object triplets, evidence documents, and fact-checking verdicts (the BEAR-Fact corpus). We find (1) that discovering evidence for negated claims (e.g., X-does-not-cause-Y) is particularly challenging. Further, we see that annotators process queries mostly by adding constraints to the search and by normalizing entities to canonical names. (2) We compare our in-house annotations with a small crowdsourcing setting where we employ medical experts and laypeople. We find that domain expertise does not have a substantial effect on the reliability of annotations. Finally, (3), we demonstrate that it is possible to reliably estimate the success of evidence retrieval purely from the claim text~(.82\F), whereas identifying unverifiable claims proves more challenging (.27\F). The dataset is available at http://www.ims.uni-stuttgart.de/data/bioclaim.