36 citations · 107 across the 24 of their papers we have counts for
24 papers
Model Unlearning Objectives Vary for Distinct Language Functions
Berk Atil, Vipul Gupta, Rebecca J. Passonneau
Large language models (LLMs) learn undesirable properties during pretraining, including dangerous knowledge and toxic text generation. Just as post-training uses different objectiv…
Robust Persona-Aware Toxicity Detection with Prompt Optimization and Learned Ensembling
Berk Atil, Rebecca J. Passonneau, Ninareh Mehrabi
Toxicity detection is inherently subjective, shaped by the diverse perspectives and social priors of different demographic groups. While ``pluralistic'' modeling as used in economi…
Do Methods to Jailbreak and Defend LLMs Generalize Across Languages?
Berk Atil, Rebecca J. Passonneau, Fred Morstatter
Large language models (LLMs) undergo safety alignment after training and tuning, yet recent work shows that safety can be bypassed through jailbreak attacks. While many jailbreaks…
Something Just Like TRuST : Toxicity Recognition of Span and Target
Berk Atil, Namrata Sureddy, Rebecca J. Passonneau
Toxic language includes content that is offensive, abusive, or that promotes harm. Progress in preventing toxic output from large language models (LLMs) is hampered by inconsistent…
Concept-based Rubrics Improve LLM Formative Assessment and Data Synthesis
Yuchen Wei, Dennis Pearl, Matthew Beckman +1
Formative assessment in STEM topics aims to promote student learning by identifying students' current understanding, thus targeting how to promote further learning. Previous studie…
Can LLMs Rank the Harmfulness of Smaller LLMs? We are Not There Yet
Berk Atil, Vipul Gupta, Sarkar Snigdha Sarathi Das +1
Large language models (LLMs) have become ubiquitous, thus it is important to understand their risks and limitations. Smaller LLMs can be deployed where compute resources are constr…
Joint Training for Selective Prediction
Zhaohui Li, Rebecca J. Passonneau
Classifier models are prevalent in natural language processing (NLP), often with high accuracy. Yet in real world settings, human-in-the-loop systems can foster trust in model outp…
Improving Model Evaluation using SMART Filtering of Benchmark Datasets
Vipul Gupta, Candace Ross, David Pantoja +3
One of the most challenging problems facing NLP today is evaluation. Some of the most pressing issues pertain to benchmark saturation, data contamination, and diversity in the qual…
Non-Determinism of "Deterministic" LLM Settings
Berk Atil, Sarp Aykent, Alexa Chittams +10
LLM (large language model) practitioners commonly notice that outputs can vary for the same inputs under settings expected to be deterministic. Yet the questions of how pervasive t…
How Well Can You Articulate that Idea? Insights from Automated Formative Assessment
Mahsa Sheikhi Karizaki, Dana Gnesdilow, Sadhana Puntambekar +1
Automated methods are becoming increasingly integrated into studies of formative feedback on students' science explanation writing. Most of this work, however, addresses students'…
VerAs: Verify then Assess STEM Lab Reports
Berk Atil, Mahsa Sheikhi Karizaki, Rebecca J. Passonneau
With an increasing focus in STEM education on critical thinking skills, science writing plays an ever more important role in curricula that stress inquiry skills. A recently publis…
The Sentiment Problem: A Critical Survey towards Deconstructing Sentiment Analysis
Pranav Narayanan Venkit, Mukund Srinath, Sanjana Gautam +4
We conduct an inquiry into the sociotechnical aspects of sentiment analysis (SA) by critically examining 189 peer-reviewed papers on their applications, models, and datasets. Our i…
CALM : A Multi-task Benchmark for Comprehensive Assessment of Language Model Bias
Vipul Gupta, Pranav Narayanan Venkit, Hugo Laurençon +2
As language models (LMs) become increasingly powerful and widely used, it is important to quantify them for sociodemographic bias with potential for harm. Prior measures of bias ar…
Sociodemographic Bias in Language Models: A Survey and Forward Path
Vipul Gupta, Pranav Narayanan Venkit, Shomir Wilson +1
Sociodemographic bias in language models (LMs) has the potential for harm when deployed in real-world settings. This paper presents a comprehensive survey of the past decade of res…
Foundations for NLP-assisted formative assessment feedback for short-answer tasks in large-enrollment classes
Susan Lloyd, Matthew Beckman, Dennis Pearl +3
Research suggests "write-to-learn" tasks improve learning outcomes, yet constructed-response methods of formative assessment become unwieldy with large class sizes. This study eval…
CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning
Sarkar Snigdha Sarathi Das, Arzoo Katiyar, Rebecca J. Passonneau +1
Named Entity Recognition (NER) in Few-Shot setting is imperative for entity tagging in low resource domains. Existing approaches only learn class-specific semantic features and int…
ABCD: A Graph Framework to Convert Complex Sentences to a Covering Set of Simple Sentences
Yanjun Gao, Ting-hao Huang, Rebecca J. Passonneau
Atomic clauses are fundamental text units for understanding complex sentences. Identifying the atomic sentences within complex sentences is important for applications such as summa…
OmniGraph: Rich Representation and Graph Kernel Learning
Boyi Xie, Rebecca J. Passonneau
OmniGraph, a novel representation to support a range of NLP classification tasks, integrates lexical items, syntactic dependencies and frame semantic parses into graphs. Feature en…
Abstractive Multi-Document Summarization via Phrase Selection and Merging
Lidong Bing, Piji Li, Yi Liao +3
We propose an abstraction-based multi-document summarization framework that can construct new sentences by exploring more fine-grained syntactic units than sentences, namely, noun/…
Leveraging Subjective Human Annotation for Clustering Historic Newspaper Articles
Haimonti Dutta, William Chan, Deepak Shankargouda +7
The New York Public Library is participating in the Chronicling America initiative to develop an online searchable database of historically significant newspaper articles. Microfil…
Applying Reliability Metrics to Co-Reference Annotation
Rebecca J. Passonneau
Studies of the contextual and linguistic factors that constrain discourse phenomena such as reference are coming to depend increasingly on annotated language corpora. In preparing…
Integrating Gricean and Attentional Constraints
Rebecca J. Passonneau
This paper concerns how to generate and understand discourse anaphoric noun phrases. I present the results of an analysis of all discourse anaphoric noun phrases (N=1,233) in a cor…
Combining Multiple Knowledge Sources for Discourse Segmentation
Diane J. Litman, Rebecca J. Passonneau
We predict discourse segment boundaries from linguistic features of utterances, using a corpus of spoken narratives as data. We present two methods for developing segmentation algo…
Intention-based Segmentation: Human Reliability and Correlation with Linguistic Cues
Rebecca J. Passonneau, Diane J. Litman
Certain spans of utterances in a discourse, referred to here as segments, are widely assumed to form coherent units. Further, the segmental structure of discourse has been claimed…