8 papers
Sycophancy Undermines Epistemic Vigilance in Cooperative Vision-Language Tasks
Rupak Sarkar, Neha Srikanth, Saloni Gupta +3
To maintain common ground in cooperative conversation, humans iteratively update their beliefs as conversation participants share new information; participants who are epistemicall…
DiscoTrace: Representing and Comparing Answering Strategies of Humans and LLMs in Information-Seeking Question Answering
Neha Srikanth, Jordan Boyd-Graber, Rachel Rudinger
We introduce DiscoTrace, a method to identify the rhetorical strategies answerers use when responding to information-seeking questions. DiscoTrace represents answers as a sequence…
NLI under the Microscope: What Atomic Hypothesis Decomposition Reveals
Neha Srikanth, Rachel Rudinger
Decomposition of text into atomic propositions is a flexible framework allowing for the closer inspection of input and output text. We use atomic decomposition of hypotheses in two…
Understanding Common Ground Misalignment in Goal-Oriented Dialog: A Case-Study with Ubuntu Chat Logs
Rupak Sarkar, Neha Srikanth, Taylor Hudson +3
While it is commonly accepted that maintaining common ground plays a role in conversational success, little prior research exists connecting conversational grounding to success in…
How often are errors in natural language reasoning due to paraphrastic variability?
Neha Srikanth, Marine Carpuat, Rachel Rudinger
Large language models have been shown to behave inconsistently in response to meaning-preserving paraphrastic inputs. At the same time, researchers evaluate the knowledge and reaso…
Pregnant Questions: The Importance of Pragmatic Awareness in Maternal Health Question Answering
Neha Srikanth, Rupak Sarkar, Heran Mane +4
Questions posed by information-seeking users often contain implicit false or potentially harmful assumptions. In a high-risk domain such as maternal and infant health, a question-a…
Partial-input baselines show that NLI models can ignore context, but they don't
Neha Srikanth, Rachel Rudinger
When strong partial-input baselines reveal artifacts in crowdsourced NLI datasets, the performance of full-input models trained on such datasets is often dismissed as reliance on s…
Elaborative Simplification: Content Addition and Explanation Generation in Text Simplification
Neha Srikanth, Junyi Jessy Li
Much of modern-day text simplification research focuses on sentence-level simplification, transforming original, more complex sentences into simplified versions. However, adding co…