LLMs struggle to associate epistemic markers with stable internal confidence levels across distributions, even under model-centric interpretations, while maintaining somewhat consistent marker rankings.
hub
Vera and Bellamy, Rachel K
21 Pith papers cite this work, alongside 1,075 external citations. Polarity classification is still indexing.
21
Pith papers citing it
1,075
external citations · external index
hub tools
citation-role summary
background 3
method 1
citation-polarity summary
representative citing papers
SEED is a structural encoding framework using typed actor-flow graphs to describe, evaluate novelty of, and generate experimental designs for AI-enabled science under feasibility and governance constraints.
Collective recourse formalizes community reports to fix group harms in diffusion models for urban visualizations via a report-triage-fix-verify pipeline, four primitives, a mandate score, and synthetic evaluation of 240 reports.
RLMF uses quality of model self-judgments to refine RL rankings and select training data, achieving SOTA faithful calibration while preserving accuracy and outperforming standard RL by up to 63%.
Derives closed-form optimal counterfactually fair regressor via barycentric quantile map and proves Õ(n^{-1/3}) finite-sample fairness and risk bounds for discretized post-processing under mild assumptions.
DEFault++ applies hierarchical learning with a Fault Propagation Graph to detect, localize, and diagnose faults in transformers, improving F1 to 0.826-0.909 and developer repair accuracy from 57.1% to 83.3% on a new benchmark of 5,556 mutation-tested runs.
Formalizing personalization as individual actionability in causal recourse shows hard constraints degrade validity and plausibility while revealing socio-demographic disparities in costs.
Adversarial explanation attacks preserve nearly all human trust in wrong AI outputs by using persuasive framing, shown in a study varying reasoning, evidence, style, and format with over 200 participants.
Cognitive forcing interventions reduce overreliance on AI recommendations more than simple explanations, with effects moderated by individual need for cognition.
Two linked user studies find that LLM rationale correctness and certainty framing affect trust and decision confidence while presentation format does not, and incorrect rationales increase gaze attention and pupil size.
EvalAI providing pro/con arguments improves provision-level accuracy and reduces misclassification distance in DSA illegal content reporting under AI error conditions versus conventional XAI.
A method that translates causal relationships into a Bipolar Argumentation Framework and applies semi-stable semantics to generate explanatory feature sets for machine learning predictions.
The paper proposes six interconnected elements of a design space to close the synergy gap in human-AI decision-making.
Mixed-methods study finds AI assistance linked to higher textual overlap with suggestions in writing tasks, and a reflective interface prototype increases user awareness of AI incorporation.
LLM reasoning traces and post-hoc explanations increase false trust in incorrect predictions, whereas contrastive dual explanations enhance users' ability to distinguish correct from incorrect AI outputs.
RUBEN discovers minimal rule sets explaining RAG LLM outputs via novel pruning and applies them to evaluate LLM safety against adversarial injections.
Interviews with 16 qualitative researchers identify efficiency, ownership, and trust as key factors shaping preferences for AI as a supportive assistant rather than a full collaborator or supervisor in qualitative data analysis.
An online experiment finds that showing users an overview of an AI's values reduces reliance on AI suggestions during writing tasks.
A qualitative-to-quantitative scoring framework is proposed to evaluate how well model-agnostic XAI methods support EU AI Act explainability requirements.
Benchmark of local explainability methods on tabular data finds explanation quality driven primarily by dataset complexity rather than model predictive performance.
citing papers explorer
-
Evaluating the False Trust Engendered by LLM Explanations
LLM reasoning traces and post-hoc explanations increase false trust in incorrect predictions, whereas contrastive dual explanations enhance users' ability to distinguish correct from incorrect AI outputs.