Sign in

Sanghee J. Kim

@sangheekim.bsky.social
24 followers 43 following 1 posts
PostsRepliesMedia
Sanghee J. Kim @sangheekim.bsky.social · 26/03/2026
Work that I enjoyed doing with Kanishka will be presented at #EACL2026! Paper: arxiv.org/abs/2510.127...
arxiv.org
Hey, wait a minute: on at-issue sensitivity in Language Models
Evaluating the naturalness of dialogue in language models (LMs) is not trivial: notions of 'naturalness' vary, and scalable quantitative metrics remain limited. This study leverages the linguistic not...
050
Reposted by Sanghee J. Kim
Kanishka Misra @kanishka.bsky.social · 21/10/2025
If I spill the tea—“Did you know Sue, Max’s gf, was a tennis champ?”—but then if you reply “They’re dating?!” I’d be a bit puzzled, since that’s not the main point! Humans can track what’s ‘at issue’ in conversation. How sensitive are LMs to this distinction? New paper w/ @sangheekim.bsky.social!
Title of our paper: “Hey, wait a minute: on at-issue sensitivity in Language Models” by Sanghee Kim and Kanishka Misra.

Below: A person says “Sue, Max’s girlfriend, was a tennis champ!”; a second person responds with “What racket does she use?” (which targets at-issue content); a third person replies with “They’re dating?” (which targets not at-issue content)
3354