1 | Lee DongWon https://moovingsloth.github.io/publication-type/1/ 1 Wowchemy (https://wowchemy.com)en-usThu, 10 Jul 2025 00:00:00 +0000 https://moovingsloth.github.io/media/sloth-icon-512.png 1 https://moovingsloth.github.io/publication-type/1/ Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations https://moovingsloth.github.io/publication/broken_tokens/ Thu, 10 Jul 2025 00:00:00 +0000 https://moovingsloth.github.io/publication/broken_tokens/ SuperBPE: Space Travel for Language Models https://moovingsloth.github.io/publication/superbpe/ Wed, 09 Jul 2025 00:00:00 +0000 https://moovingsloth.github.io/publication/superbpe/ Tulu 3: Pushing Frontiers in Open Language Model Post-Training https://moovingsloth.github.io/publication/tulu3/ Tue, 08 Jul 2025 00:00:00 +0000 https://moovingsloth.github.io/publication/tulu3/ Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models https://moovingsloth.github.io/publication/semantic_leakage/ Sat, 10 May 2025 00:00:00 +0000 https://moovingsloth.github.io/publication/semantic_leakage/ LlamaPIE: Proactive In-Ear Conversation Assistants https://moovingsloth.github.io/publication/llamapie/ Wed, 07 May 2025 00:00:00 +0000 https://moovingsloth.github.io/publication/llamapie/ Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data? https://moovingsloth.github.io/publication/bpe/ Tue, 23 Jul 2024 00:00:00 +0000 https://moovingsloth.github.io/publication/bpe/ We're Afraid Language Models Aren't Modeling Ambiguity https://moovingsloth.github.io/publication/ambient/ Fri, 20 Oct 2023 00:00:00 +0000 https://moovingsloth.github.io/publication/ambient/ That was the last straw, we need more: Are Translation Systems Sensitive to Disambiguating Context? https://moovingsloth.github.io/publication/tide/ Thu, 19 Oct 2023 00:00:00 +0000 https://moovingsloth.github.io/publication/tide/ Inverse Scaling: When Bigger Isn't Better https://moovingsloth.github.io/publication/inverse_scaling/ Wed, 18 Oct 2023 00:00:00 +0000 https://moovingsloth.github.io/publication/inverse_scaling/ How Language Model Hallucinations Can Snowball https://moovingsloth.github.io/publication/snowballing/ Mon, 22 May 2023 00:00:00 +0000 https://moovingsloth.github.io/publication/snowballing/ Self-Instruct: Aligning Language Models with Self-Generated Instructions https://moovingsloth.github.io/publication/self_instruct/ Wed, 21 Dec 2022 00:00:00 +0000 https://moovingsloth.github.io/publication/self_instruct/ Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts https://moovingsloth.github.io/publication/marco/ Tue, 20 Dec 2022 00:00:00 +0000 https://moovingsloth.github.io/publication/marco/ WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation https://moovingsloth.github.io/publication/wanli/ Sat, 15 Jan 2022 00:00:00 +0000 https://moovingsloth.github.io/publication/wanli/ Generated Knowledge Prompting for Commonsense Reasoning https://moovingsloth.github.io/publication/knowledge_gen/ Sat, 01 Jan 2022 00:00:00 +0000 https://moovingsloth.github.io/publication/knowledge_gen/ DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts https://moovingsloth.github.io/publication/dexperts/ Mon, 02 Aug 2021 00:00:00 +0000 https://moovingsloth.github.io/publication/dexperts/ Model Selection for Deep Audio Source Separation via Clustering Analysis https://moovingsloth.github.io/publication/ensemble/ Mon, 02 Nov 2020 00:00:00 +0000 https://moovingsloth.github.io/publication/ensemble/ Bach or Mock? A Grading Function for Chorales in the Style of J.S. Bach https://moovingsloth.github.io/publication/grading_function/ Sat, 18 Jul 2020 00:00:00 +0000 https://moovingsloth.github.io/publication/grading_function/ Incorporating Music Knowledge in Continual Dataset Augmentation for Music Generation https://moovingsloth.github.io/publication/aug_gen/ Sat, 18 Jul 2020 00:00:00 +0000 https://moovingsloth.github.io/publication/aug_gen/ CODAH: An Adversarially-Authored Question Answering Dataset for Common Sense https://moovingsloth.github.io/publication/codah/ Sat, 01 Jun 2019 00:00:00 +0000 https://moovingsloth.github.io/publication/codah/