Multi-label classification is prevalent in real-world settings, but the behavior of Large Language Models (LLMs) in this setting is understudied. We investigate how autoregressive LLMs perform multi-label classification, focusing on subjective tasks, by analyzing the output distributions of the models at each label generation step. We find that the initial probability distribution for the first label often does not reflect the eventual final output, even in terms of relative order and find LLMs tend to suppress all but one label at each generation step. We further observe that as model scale increases, their token distributions exhibit lower entropy and higher single-label confidence, but the internal relative ranking of the labels improves. Finetuning methods such as supervised finetuning and reinforcement learning amplify this phenomenon. We introduce the task of distribution alignment for multi-label settings: aligning LLM-derived label distributions with empirical distributions estimated from annotator responses in subjective tasks. We propose both zero-shot and supervised methods which improve both alignment and predictive performance over existing approaches. We find one method – taking the max probability over all label generation distributions instead of just using the initial probability distribution – improves both distribution alignment and overall F1 classification without adding any additional computation.

Modeling complex subjective tasks in Natural Language Processing, such as recognizing emotion and morality, is considerably challenging due to significant variation in human annotations. This variation often reflects reasonable differences in semantic interpretations rather than mere noise, necessitating methods to distinguish between legitimate subjectivity and error.We address this challenge by exploring label verification in these contexts using Large Language Models (LLMs). First, we propose a simple In-Context Learning binary filtering baseline that estimates the reasonableness of a document-label pair. We then introduce the Label-in-a-Haystack setting: the query and its label(s) are included in the demonstrations shown to LLMs, which are prompted to predict the label(s) again, while receiving task-specific instructions (e.g., emotion recognition) rather than label copying.We show how the failure to copy the label(s) to the output of the LLM are task-relevant and informative. Building on this, we propose the Label-in-a-Haystack Rectification (LiaHR) framework for subjective label correction: when the model outputs diverge from the reference gold labels, we assign the generated labels to the example instead of discarding it. This approach can be integrated into annotation pipelines to enhance signal-to-noise ratios. Comprehensive analyses, human evaluations, and ecological validity studies verify the utility of LiaHR for label correction. Code is available at https://github.com/gchochla/liahr.

Large vision-language models (VLMs) have demonstrated remarkable abilities in understanding everyday content. However, their performance in the domain of art, particularly culturally rich art forms, remains less explored. As a pearl of human wisdom and creativity, art encapsulates complex cultural narratives and symbolism. In this paper, we offer the Pun Rebus Art Dataset, a multimodal dataset for art understanding deeply rooted in traditional Chinese culture. We focus on three primary tasks: identifying salient visual elements, matching elements with their symbolic meanings, and explanations for the conveyed messages. Our evaluation reveals that state-of-the-art VLMs struggle with these tasks, often providing biased and hallucinated explanations and showing limited improvement through in-context learning. By releasing the Pun Rebus Art Dataset, we aim to facilitate the development of VLMs that can better understand and interpret culturally specific content, promoting greater inclusiveness beyond English-based corpora. The dataset and evaluation code are available at [this link](https://github.com/zhang-tuo-pdf/Pun-Rebus-Art-Benchmark).

In-context Learning (ICL) has become the primary method for performing natural language tasks with Large Language Models (LLMs). The knowledge acquired during pre-training is crucial for this few-shot capability, providing the model with task priors. However, recent studies have shown that ICL predominantly relies on retrieving task priors rather than “learning” to perform tasks. This limitation is particularly evident in complex subjective domains such as emotion and morality, where priors significantly influence posterior predictions. In this work, we examine whether this is the result of the aggregation used in corresponding datasets, where trying to combine low-agreement, disparate annotations might lead to annotation artifacts that create detrimental noise in the prompt. Moreover, we evaluate the posterior bias towards certain annotators by grounding our study in appropriate, quantitative measures of LLM priors. Our results indicate that aggregation is a confounding factor in the modeling of subjective tasks, and advocate focusing on modeling individuals instead. However, aggregation does not explain the entire gap between ICL and the state of the art, meaning other factors in such tasks also account for the observed phenomena. Finally, by rigorously studying annotator-level labels, we find that it is possible for minority annotators to both better align with LLMs and have their perspectives further amplified.

Computational narrative understanding studies the identification, description, and interaction of the elements of a narrative: characters, attributes, events, and relations.Narrative research has given considerable attention to defining and classifying character types.However, these character-type taxonomies do not generalize well because they are small, too simple, or specific to a domain.We require robust and reliable benchmarks to test whether narrative models truly understand the nuances of the character’s development in the story.Our work addresses this by curating the CHATTER dataset that labels whether a character portrays some attribute for 88124 character-attribute pairs, encompassing 2998 characters, 12967 attributes and 660 movies.We validate a subset of CHATTER, called CHATTEREVAL, using human annotations to serve as an evaluation benchmark for the character attribution task in movie scripts.CHATTEREVAL also assesses narrative understanding and the long-context modeling capacity of language models.

Movie screenplays have a distinct narrative structure. It segments the story into scenes containing interleaving descriptions of actions, locations, and character dialogues.A typical screenplay spans several scenes and can include long-range dependencies between characters and events.A holistic document-level understanding of the screenplay requires several natural language processing capabilities, such as parsing, character identification, coreference resolution, action recognition, summarization, and attribute discovery. In this work, we develop scalable and robust methods to extract the structural information and character coreference clusters from full-length movie screenplays. We curate two datasets for screenplay parsing and character coreference — MovieParse and MovieCoref, respectively.We build a robust screenplay parser to handle inconsistencies in screenplay formatting and leverage the parsed output to link co-referring character mentions.Our coreference models can scale to long screenplay documents without drastically increasing their memory footprints.

Sentiment analysis is a costly yet necessary task for enterprises to study the opinions of their customers to improve their products and to determine optimal marketing strategies. Due to the existence of a wide range of domains across different products and services, cross-domain sentiment analysis methods have received significant attention. These methods mitigate the domain gap between different applications by training cross-domain generalizable classifiers which relax the need for data annotation for each domain. We develop a domain adaptation method which induces large margins between data representations that belong to different classes in an embedding space. This embedding space is trained to be domain-agnostic by matching the data distributions across the domains. Large interclass margins in the source domain help to reduce the effect of “domain shift” in the target domain. Theoretical and empirical analysis are provided to demonstrate that the proposed method is effective.

In psychotherapy interactions, the quality of a session is assessed by codifying the communicative behaviors of participants during the conversation through manual observation and annotation. Developing computational approaches for automated behavioral coding can reduce the burden on human coders and facilitate the objective evaluation of the intervention. In the real world, however, implementing such algorithms is associated with data sparsity challenges since privacy concerns lead to limited available in-domain data. In this paper, we leverage a publicly available conversation-based dataset and transfer knowledge to the low-resource behavioral coding task by performing an intermediate language model training via meta-learning. We introduce a task augmentation method to produce a large number of “analogy tasks” — tasks similar to the target one — and demonstrate that the proposed framework predicts target behaviors more accurately than all the other baseline models.

Spoken language understanding tasks usually rely on pipelines involving complex processing blocks such as voice activity detection, speaker diarization and Automatic speech recognition (ASR). We propose a novel framework for predicting utterance level labels directly from speech features, thus removing the dependency on first generating transcripts, and transcription free behavioral coding. Our classifier uses a pretrained Speech-2-Vector encoder as bottleneck to generate word-level representations from speech features. This pretrained encoder learns to encode speech features for a word using an objective similar to Word2Vec. Our proposed approach just uses speech features and word segmentation information for predicting spoken utterance-level target labels. We show that our model achieves competitive results to other state-of-the-art approaches which use transcribed text for the task of predicting psychotherapy-relevant behavior codes.

Exposure to violent, sexual, or substance-abuse content in media increases the willingness of children and adolescents to imitate similar behaviors. Computational methods that identify portrayals of risk behaviors from audio-visual cues are limited in their applicability to films in post-production, where modifications might be prohibitively expensive. To address this limitation, we propose a model that estimates content ratings based on the language use in movie scripts, making our solution available at the earlier stages of creative production. Our model significantly improves the state-of-the-art by adapting novel techniques to learn better movie representations from the semantic and sentiment aspects of a character’s language use, and by leveraging the co-occurrence of risk behaviors, following a multi-task approach. Additionally, we show how this approach can be useful to learn novel insights on the joint portrayal of these behaviors, and on the subtleties that filmmakers may otherwise not pick up on.

Deciding which scripts to turn into movies is a costly and time-consuming process for filmmakers. Thus, building a tool to aid script selection, an initial phase in movie production, can be very beneficial. Toward that goal, in this work, we present a method to evaluate the quality of a screenplay based on linguistic cues. We address this in a two-fold approach: (1) we define the task as predicting nominations of scripts at major film awards with the hypothesis that the peer-recognized scripts should have a greater chance to succeed. (2) based on industry opinions and narratology, we extract and integrate domain-specific features into common classification techniques. We face two challenges (1) scripts are much longer than other document datasets (2) nominated scripts are limited and thus difficult to collect. However, with narratology-inspired modeling and domain features, our approach offers clear improvements over strong baselines. Our work provides a new approach for future work in screenplay analysis.

We present a novel multi-task modeling approach to learning multilingual distributed representations of text. Our system learns word and sentence embeddings jointly by training a multilingual skip-gram model together with a cross-lingual sentence similarity model. Our architecture can transparently use both monolingual and sentence aligned bilingual corpora to learn multilingual embeddings, thus covering a vocabulary significantly larger than the vocabulary of the bilingual corpora alone. Our model shows competitive performance in a standard cross-lingual document classification task. We also show the effectiveness of our method in a limited resource scenario.

In this paper we present deep-learning models that submitted to the SemEval-2018 Task 1 competition: “Affect in Tweets”. We participated in all subtasks for English tweets. We propose a Bi-LSTM architecture equipped with a multi-layer self attention mechanism. The attention mechanism improves the model performance and allows us to identify salient words in tweets, as well as gain insight into the models making them more interpretable. Our model utilizes a set of word2vec word embeddings trained on a large collection of 550 million Twitter messages, augmented by a set of word affective features. Due to the limited amount of task-specific training data, we opted for a transfer learning approach by pretraining the Bi-LSTMs on the dataset of Semeval 2017, Task 4A. The proposed approach ranked 1st in Subtask E “Multi-Label Emotion Classification”, 2nd in Subtask A “Emotion Intensity Regression” and achieved competitive results in other subtasks.

We examine differences in portrayal of characters in movies using psycholinguistic and graph theoretic measures computed directly from screenplays. Differences are examined with respect to characters’ gender, race, age and other metadata. Psycholinguistic metrics are extrapolated to dialogues in movies using a linear regression model built on a set of manually annotated seed words. Interesting patterns are revealed about relationships between genders of production team and the gender ratio of characters. Several correlations are noted between gender, race, age of characters and the linguistic metrics.

In this paper, we describe our submission to SemEval2017 Task 4: Sentiment Analysis in Twitter. Specifically the proposed system participated both to tweet polarity classification (two-, three- and five class) and tweet quantification (two and five-class) tasks.

The Twins corpus is a collection of utterances spoken in interactions with two virtual characters who serve as guides at the Museum of Science in Boston. The corpus contains about 200,000 spoken utterances from museum visitors (primarily children) as well as from trained handlers who work at the museum. In addition to speech recordings, the corpus contains the outputs of speech recognition performed at the time of utterance as well as the system interpretation of the utterances. Parts of the corpus have been manually transcribed and annotated for question interpretation. The corpus has been used for improving performance of the museum characters and for a variety of research projects, such as phonetic-based Natural Language Understanding, creation of conversational characters from text resources, dialogue policy learning, and research on patterns of user interaction. It has the potential to be used for research on children's speech and on language used when talking to a virtual human.