23 citations · 65 across the 30 of their papers we have counts for
26 papers · 1 filter
Side-by-side Comparison Amplifies Dialect Bias in Language Models
Kritee Kondapally, Claire J. Smerdon, Pooja C. Patel +5
Language models (LMs) can exhibit biases based on variations in their dialects, even in the absence of a dialect label, a behavior known as covert dialect bias. In this work, we qu…
BenchBrowser: Retrieving Evidence for Evaluating Benchmark Validity
Harshita Diddee, Gregory Yauney, Swabha Swayamdipta +1
Do language model benchmarks actually measure what practitioners intend them to ? High-level metadata is too coarse to convey the granular reality of benchmarks: a "poetry" benchma…
Why Fine-Tuning Encourages Hallucinations and How to Fix It
Guy Kaplan, Zorik Gekhman, Zhen Zhu +5
Large language models are prone to hallucinating factually incorrect statements. A key source of these errors is exposure to new factual information through supervised fine-tuning…
Disentangling Geometry, Performance, and Training in Language Models
Atharva Kulkarni, Jacob Mitchell Springer, Arjun Subramonian +1
Geometric properties of Transformer weights, particularly the unembedding matrix, have been widely useful in language model interpretability research. Yet, their utility for estima…
Believing without Seeing: Quality Scores for Contextualizing Vision-Language Model Explanations
Keyu He, Tejas Srinivasan, Brihi Joshi +3
When people query Vision-Language Models (VLMs) but cannot see the accompanying visual context (e.g. for blind and low-vision users), augmenting VLM predictions with natural langua…
ELI-Why: Evaluating the Pedagogical Utility of Language Model Explanations
Brihi Joshi, Keyu He, Sahana Ramnath +5
Language models today are widely used in education, yet their ability to tailor responses for learners with varied informational needs and knowledge backgrounds remains under-explo…
Better Language Model Inversion by Compactly Representing Next-Token Distributions
Murtaza Nazir, Matthew Finlayson, John X. Morris +2
Language model inversion seeks to recover hidden prompts using only language model outputs. This capability has implications for security and accountability in language model deplo…
Improving Language Model Personas via Rationalization with Psychological Scaffolds
Brihi Joshi, Xiang Ren, Swabha Swayamdipta +2
Language models prompted with a user description or persona are being used to predict the user's preferences and opinions. However, existing approaches to building personas mostly…
Teaching Models to Understand (but not Generate) High-risk Data
Ryan Wang, Matthew Finlayson, Luca Soldaini +2
Language model developers typically filter out high-risk content -- such as toxic or copyrighted text -- from their pre-training data to prevent models from generating similar outp…
Evaluating Evaluation Metrics -- The Mirage of Hallucination Detection
Atharva Kulkarni, Yuan Zhang, Joel Ruben Antony Moniz +5
Hallucinations pose a significant obstacle to the reliability and widespread adoption of language models, yet their accurate measurement remains a persistent challenge. While many…
Political-LLM: Large Language Models in Political Science
Lincan Li, Jiaqi Li, Catherine Chen +44
In recent years, large language models (LLMs) have been widely adopted in political science tasks such as election prediction, sentiment analysis, policy impact assessment, and mis…
Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?
Urja Khurana, Eric Nalisnick, Antske Fokkens +1
Subjective tasks in NLP have been mostly relegated to objective standards, where the gold label is decided by taking the majority vote. This obfuscates annotator disagreement and t…
Logits of API-Protected LLMs Leak Proprietary Information
Matthew Finlayson, Xiang Ren, Swabha Swayamdipta
Large language model (LLM) providers often hide the architectural details and parameters of their proprietary models by restricting public access to a limited API. In this work we…
Closing the Curious Case of Neural Text Degeneration
Matthew Finlayson, John Hewitt, Alexander Koller +2
Despite their ubiquity in language generation, it remains unknown why truncation sampling heuristics like nucleus sampling are so effective. We provide a theoretical explanation fo…
COBRA Frames: Contextual Reasoning about Effects and Harms of Offensive Statements
Xuhui Zhou, Hao Zhu, Akhila Yerukola +4
Warning: This paper contains content that may be offensive or upsetting. Understanding the harms and offensiveness of statements requires reasoning about the social and situational…
NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge
Phillip Howard, Junlin Wang, Vasudev Lal +3
Comparative knowledge (e.g., steel is stronger and heavier than styrofoam) is an essential component of our world knowledge, yet understudied in prior literature. In this paper, we…
We're Afraid Language Models Aren't Modeling Ambiguity
Alisa Liu, Zhaofeng Wu, Julian Michael +6
Ambiguity is an intrinsic feature of natural language. Managing ambiguity is a key part of human language understanding, allowing us to anticipate misunderstanding as communicators…
I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation
Chandra Bhagavatula, Jena D. Hwang, Doug Downey +7
Commonsense capabilities of pre-trained language models dramatically improve with scale, leading many to believe that scale is the only winning recipe. But is it? Here, we investig…
NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation
Phillip Howard, Gadi Singer, Vasudev Lal +2
While counterfactual data augmentation offers a promising step towards robust generalization in natural language processing, producing a set of counterfactuals that offer valuable…
REV: Information-Theoretic Evaluation of Free-Text Rationales
Hanjie Chen, Faeze Brahman, Xiang Ren +3
Generating free-text rationales is a promising step towards explainable NLP, yet evaluating such rationales remains a challenge. Existing metrics have mostly focused on measuring t…
Investigating the Benefits of Free-Form Rationales
Jiao Sun, Swabha Swayamdipta, Jonathan May +1
Free-form rationales aim to aid model interpretability by supplying the background knowledge that can help understand model decisions. Crowdsourced rationales are provided for comm…
WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation
Alisa Liu, Swabha Swayamdipta, Noah A. Smith +1
A recurring challenge of crowdsourcing NLP datasets at scale is that human writers often rely on repetitive patterns when crafting examples, leading to a lack of linguistic diversi…
Reframing Human-AI Collaboration for Generating Free-Text Explanations
Sarah Wiegreffe, Jack Hessel, Swabha Swayamdipta +2
Large language models are increasingly capable of generating fluent-appearing text with relatively little task-specific supervision. But can these models accurately explain classif…
Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection
Maarten Sap, Swabha Swayamdipta, Laura Vianna +3
The perceived toxicity of language can vary based on someone's identity and beliefs, but this variation is often ignored when collecting toxic language datasets, resulting in datas…