The rich, community-sensitive answering behavior structurally revealed by DiscoTrace can guide the development of pragmatic LLM answerers that are more attuned to contextual information needs.
Neha Srikanth, J. Boyd-Graber, Rachel Rudinger· arXiv.org· 2 citations· ⚡1
While agents aid initial task completion, they harm users' code comprehension and thus do not prepare users to extend their code, and low-effort agent interaction types, like copy+paste prompts and auto-accepted edits, are linked with lower comprehension.
This work shows that truth representations of a proposition are significantly swayed by partner assertions about that proposition, even when the LLM has enough evidence to determine its truth, and finds evidence that propositions near the decision boundary are more susceptible to having their truth shifted through part...
VibeJam, a browser-based user study platform for users to collaborate with AI agents to develop websites, and open-source VibeJam to spur extensions and support studies on how coding agents can help users.
Nishant Balepur, Connor Baumler, Valerie Chen et al.· 0 citations
It is examined how alternatives to number right change what MCQA measures with six education-inspired schemes that assess abilities beyond accuracy: distractor elimination, abstention, confidence calibration, and self-correction.
Nishant Balepur, Paiheng Xu, Wei Ai et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
