Mimansa Jaiswal

Shachar Don-Yehiya, Ben Burtenshaw, Ramon Fernandez Astudillo et al. · huggingface, ibm-research

Human feedback on conversations with language language models (LLMs) is central to how these systems learn about the world, improve their capabilities, and are steered toward desirable and safe behaviors. However, this feedback is mostly collected by frontier AI labs and kept behind closed doors. In this work, we bring together interdisciplinary experts to assess the opportunities and challenges to realizing an open ecosystem of human feedback for AI. We first look for successful practices in peer production, open source, and citizen science communities. We then characterize the main challenges for open human feedback. For each, we survey current approaches and offer recommendations. We end by envisioning the components needed to underpin a sustainable and open human feedback ecosystem. In the center of this ecosystem are mutually beneficial feedback loops, between users and specialized models, incentivizing a diverse stakeholders community of model trainers and feedback providers to support a general open feedback pool.

Minxue Niu, Mimansa Jaiswal, Emily Mower Provost

Training emotion recognition models has relied heavily on human annotated data, which present diversity, quality, and cost challenges. In this paper, we explore the potential of Large Language Models (LLMs), specifically GPT4, in automating or assisting emotion annotation. We compare GPT4 with supervised models and or humans in three aspects: agreement with human annotations, alignment with human perception, and impact on model training. We find that common metrics that use aggregated human annotations as ground truth can underestimate the performance, of GPT-4 and our human evaluation experiment reveals a consistent preference for GPT-4 annotations over humans across multiple datasets and evaluators. Further, we investigate the impact of using GPT-4 as an annotation filtering process to improve model training. Together, our findings highlight the great potential of LLMs in emotion annotation tasks and underscore the need for refined evaluation methodologies.

Stella Biderman, Hailey Schoelkopf, Lintang Sutawika et al. · cmu

Effective evaluation of language models remains an open challenge in NLP. Researchers and engineers face methodological issues such as the sensitivity of models to evaluation setup, difficulty of proper comparisons across methods, and the lack of reproducibility and transparency. In this paper we draw on three years of experience in evaluating large language models to provide guidance and lessons for researchers. First, we provide an overview of common challenges faced in language model evaluation. Second, we delineate best practices for addressing or lessening the impact of these challenges on research. Third, we present the Language Model Evaluation Harness (lm-eval): an open source library for independent, reproducible, and extensible evaluation of language models that seeks to address these issues. We describe the features of the library as well as case studies in which the library has been used to alleviate these methodological concerns.

Mimansa Jaiswal

Emotion recognition is a complex task due to the inherent subjectivity in both the perception and production of emotions. The subjectivity of emotions poses significant challenges in developing accurate and robust computational models. This thesis examines critical facets of emotion recognition, beginning with the collection of diverse datasets that account for psychological factors in emotion production. To handle the challenge of non-representative training data, this work collects the Multimodal Stressed Emotion dataset, which introduces controlled stressors during data collection to better represent real-world influences on emotion production. To address issues with label subjectivity, this research comprehensively analyzes how data augmentation techniques and annotation schemes impact emotion perception and annotator labels. It further handles natural confounding variables and variations by employing adversarial networks to isolate key factors like stress from learned emotion representations during model training. For tackling concerns about leakage of sensitive demographic variables, this work leverages adversarial learning to strip sensitive demographic information from multimodal encodings. Additionally, it proposes optimized sociological evaluation metrics aligned with cost-effective, real-world needs for model testing. This research advances robust, practical emotion recognition through multifaceted studies of challenges in datasets, labels, modeling, demographic and membership variable encoding in representations, and evaluation. The groundwork has been laid for cost-effective, generalizable emotion recognition models that are less likely to encode sensitive demographic information.

Mimansa Jaiswal, Emily Mower Provost

Speech emotion recognition is an important component of any human centered system. But speech characteristics produced and perceived by a person can be influenced by a multitude of reasons, both desirable such as emotion, and undesirable such as noise. To train robust emotion recognition models, we need a large, yet realistic data distribution, but emotion datasets are often small and hence are augmented with noise. Often noise augmentation makes one important assumption, that the prediction label should remain the same in presence or absence of noise, which is true for automatic speech recognition but not necessarily true for perception based tasks. In this paper we make three novel contributions. We validate through crowdsourcing that the presence of noise does change the annotation label and hence may alter the original ground truth label. We then show how disregarding this knowledge and assuming consistency in ground truth labels propagates to downstream evaluation of ML models, both for performance evaluation and robustness testing. We end the paper with a set of recommendations for noise augmentations in speech emotion recognition datasets.

Mimansa Jaiswal, Emily Mower Provost

Privacy preservation is a crucial component of any real-world application. But, in applications relying on machine learning backends, privacy is challenging because models often capture more than what the model was initially trained for, resulting in the potential leakage of sensitive information. In this paper, we propose an automatic and quantifiable metric that allows us to evaluate humans' perception of a model's ability to preserve privacy with respect to sensitive variables. In this paper, we focus on saliency-based explanations, explanations that highlight regions of the input text, to infer internal workings of a black box model. We use the degree with which differences in interpretation of general vs privacy preserving models correlate with sociolinguistic biases to inform metric design. We show how certain commonly-used methods that seek to preserve privacy do not align with human perception of privacy preservation leading to distrust about model's claims. We demonstrate the versatility of our proposed metric by validating its utility for measuring cross corpus generalization for both privacy and emotion. Finally, we conduct crowdsourcing experiments to evaluate the inclination of the evaluators to choose a particular model for a given purpose when model explanations are provided, and show a positive relationship with the proposed metric. To the best of our knowledge, we take the first step in proposing automatic and quantifiable metrics that best align with human perception of model's ability for privacy preservation, allowing for cost-effective model development.

Mimansa Jaiswal, Emily Mower Provost

Many mobile applications and virtual conversational agents now aim to recognize and adapt to emotions. To enable this, data are transmitted from users' devices and stored on central servers. Yet, these data contain sensitive information that could be used by mobile applications without user's consent or, maliciously, by an eavesdropping adversary. In this work, we show how multimodal representations trained for a primary task, here emotion recognition, can unintentionally leak demographic information, which could override a selected opt-out option by the user. We analyze how this leakage differs in representations obtained from textual, acoustic, and multimodal data. We use an adversarial learning paradigm to unlearn the private information present in a representation and investigate the effect of varying the strength of the adversarial component on the primary task and on the privacy metric, defined here as the inability of an attacker to predict specific demographic information. We evaluate this paradigm on multiple datasets and show that we can improve the privacy metric while not significantly impacting the performance on the primary task. To the best of our knowledge, this is the first work to analyze how the privacy metric differs across modalities and how multiple privacy concerns can be tackled while still maintaining performance on emotion recognition.

Zakaria Aldeneh, Mimansa Jaiswal, Michael Picheny et al.

Bipolar disorder, a severe chronic mental illness characterized by pathological mood swings from depression to mania, requires ongoing symptom severity tracking to both guide and measure treatments that are critical for maintaining long-term health. Mental health professionals assess symptom severity through semi-structured clinical interviews. During these interviews, they observe their patients' spoken behaviors, including both what the patients say and how they say it. In this work, we move beyond acoustic and lexical information, investigating how higher-level interactive patterns also change during mood episodes. We then perform a secondary analysis, asking if these interactive patterns, measured through dialogue features, can be used in conjunction with acoustic features to automatically recognize mood episodes. Our results show that it is beneficial to consider dialogue features when analyzing and building automated systems for predicting and monitoring mood.

Mimansa Jaiswal, Zakaria Aldeneh, Emily Mower Provost

Various psychological factors affect how individuals express emotions. Yet, when we collect data intended for use in building emotion recognition systems, we often try to do so by creating paradigms that are designed just with a focus on eliciting emotional behavior. Algorithms trained with these types of data are unlikely to function outside of controlled environments because our emotions naturally change as a function of these other factors. In this work, we study how the multimodal expressions of emotion change when an individual is under varying levels of stress. We hypothesize that stress produces modulations that can hide the true underlying emotions of individuals and that we can make emotion recognition algorithms more generalizable by controlling for variations in stress. To this end, we use adversarial networks to decorrelate stress modulations from emotion representations. We study how stress alters acoustic and lexical emotional predictions, paying special attention to how modulations due to stress affect the transferability of learned emotion recognition models across domains. Our results show that stress is indeed encoded in trained emotion classifiers and that this encoding varies across levels of emotions and across the lexical and acoustic modalities. Our results also show that emotion recognition models that control for stress during training have better generalizability when applied to new domains, compared to models that do not control for stress during training. We conclude that is is necessary to consider the effect of extraneous psychological factors when building and testing emotion recognition models.

Mimansa Jaiswal, Zakaria Aldeneh, Cristian-Paul Bara et al.

Emotion recognition algorithms rely on data annotated with high quality labels. However, emotion expression and perception are inherently subjective. There is generally not a single annotation that can be unambiguously declared "correct". As a result, annotations are colored by the manner in which they were collected. In this paper, we conduct crowdsourcing experiments to investigate this impact on both the annotations themselves and on the performance of these algorithms. We focus on one critical question: the effect of context. We present a new emotion dataset, Multimodal Stressed Emotion (MuSE), and annotate the dataset using two conditions: randomized, in which annotators are presented with clips in random order, and contextualized, in which annotators are presented with clips in order. We find that contextual labeling schemes result in annotations that are more similar to a speaker's own self-reported labels and that labels generated from randomized schemes are most easily predictable by automated systems.

Mimansa Jaiswal, Sairam Tabibu, Erik Cambria

In the past few years, social media has risen as a platform where people express and share personal incidences about abuse, violence and mental health issues. There is a need to pinpoint such posts and learn the kind of response expected. For this purpose, we understand the sentiment that a personal story elicits on different posts present on different social media sites, on the topics of abuse or mental health. In this paper, we propose a method supported by hand-crafted features to judge if the post requires an empathetic response. The model is trained upon posts from various web-pages and corresponding comments, on both the captions and the images. We were able to obtain 80% accuracy in tagging posts requiring empathetic responses.

Mimansa Jaiswal, Sairam Tabibu, Rajiv Bajpai

We propose a data-driven method for automatic deception detection in real-life trial data using visual and verbal cues. Using OpenFace with facial action unit recognition, we analyze the movement of facial features of the witness when posed with questions and the acoustic patterns using OpenSmile. We then perform a lexical analysis on the spoken words, emphasizing the use of pauses and utterance breaks, feeding that to a Support Vector Machine to test deceit or truth prediction. We then try out a method to incorporate utterance-based fusion of visual and lexical analysis, using string based matching.

Soheil Khorram, Mimansa Jaiswal, John Gideon et al.

Bipolar Disorder is a chronic psychiatric illness characterized by pathological mood swings associated with severe disruptions in emotion regulation. Clinical monitoring of mood is key to the care of these dynamic and incapacitating mood states. Frequent and detailed monitoring improves clinical sensitivity to detect mood state changes, but typically requires costly and limited resources. Speech characteristics change during both depressed and manic states, suggesting automatic methods applied to the speech signal can be effectively used to monitor mood state changes. However, speech is modulated by many factors, which renders mood state prediction challenging. We hypothesize that emotion can be used as an intermediary step to improve mood state prediction. This paper presents critical steps in developing this pipeline, including (1) a new in the wild emotion dataset, the PRIORI Emotion Dataset, collected from everyday smartphone conversational speech recordings, (2) activation/valence emotion recognition baselines on this dataset (PCC of 0.71 and 0.41, respectively), and (3) significant correlation between predicted emotion and mood state for individuals with bipolar disorder. This provides evidence and a working baseline for the use of emotion as a meta-feature for mood state monitoring.