PhD student @ CMU LTI. working on text generation + long context https://www.cs.cmu.edu/~abertsch/https://bsky.app/profile/abertsch.bsky.socialhttps://bsky.app/profile/abertsch.bsky.social/post/3m52kvdb2os22Can LLMs accurately aggregate information over long, information-dense texts? Not yet… We introduce Oolong, a dataset of simple-to-verify information aggregation questions over long inputs. No model achieves >50% accuracy at 128K on Oolong!07 Nov 2025 17:07 +0000at://did:plc:qdcrfb2oqtak4eddiy62j2dc/app.bsky.feed.post/3m52kvdb2os22https://bsky.app/profile/abertsch.bsky.social/post/3lynr7kjlq22i. @gneubig.bsky.social and I are co-teaching a new class on LM inference this fall! We designed this class to give a broad view on the space, from more classical decoding algorithms to recent methods for LLMs, plus a wide range of efficiency-focused work. website: https://phontron.com/class/lminference-fall2025/12 Sep 2025 17:14 +0000at://did:plc:qdcrfb2oqtak4eddiy62j2dc/app.bsky.feed.post/3lynr7kjlq22ihttps://bsky.app/profile/abertsch.bsky.social/post/3lnyima6bhs2psuper excited to see folks at #NAACL25 this week! I'll be presenting our work on long-context ICL Wednesday in the 2pm poster session in Hall 3-- would love to chat with folks there or at the rest of the conference about long context data, ICL, inference time methods, New Mexican food, etc :)30 Apr 2025 00:03 +0000at://did:plc:qdcrfb2oqtak4eddiy62j2dc/app.bsky.feed.post/3lnyima6bhs2p