Hanbo Xie
@psychboyh.bsky.social
Fourth-year PhD student at NRD Lab at Gatech. Interested in how humans and AI think and reason.
Pinned
Hanbo Xie
@psychboyh.bsky.social
· Oct 2
Can Think-Aloud be really useful in understanding human minds? Building on our previous work, we formally propose reopening this old debate, with one of the largest Think-Aloud datasets, "RiskyThought44K," and LLM analysis, showing Think-Aloud can complement to comp cogsci.
I am excited to share that our paper is accepted by @neuripsconf.bsky.social . This is an interesting work that uses tools and insights from comp cog neuroscience to understand LLMs. Nice work by @louannapan.bsky.social and @doctor-bob.bsky.social.
Large Language Models can do a lot of things. But do you know they cannot explore effectively, especially in open-ended tasks? Recently, Lan Pan and I dropped a preprint to investigate how LLMs explore in an open-ended task.
arxiv.org/abs/2501.18009
arxiv.org/abs/2501.18009
Large Language Models Think Too Fast To Explore Effectively
Large Language Models have emerged many intellectual capacities. While numerous benchmarks assess their intelligence, limited attention has been given to their ability to explore, an essential capacit...
arxiv.org
October 6, 2025 at 5:44 PM
I am excited to share that our paper is accepted by @neuripsconf.bsky.social . This is an interesting work that uses tools and insights from comp cog neuroscience to understand LLMs. Nice work by @louannapan.bsky.social and @doctor-bob.bsky.social.
Can Think-Aloud be really useful in understanding human minds? Building on our previous work, we formally propose reopening this old debate, with one of the largest Think-Aloud datasets, "RiskyThought44K," and LLM analysis, showing Think-Aloud can complement to comp cogsci.
October 2, 2025 at 3:06 AM
Can Think-Aloud be really useful in understanding human minds? Building on our previous work, we formally propose reopening this old debate, with one of the largest Think-Aloud datasets, "RiskyThought44K," and LLM analysis, showing Think-Aloud can complement to comp cogsci.
Large Language Models can do a lot of things. But do you know they cannot explore effectively, especially in open-ended tasks? Recently, Lan Pan and I dropped a preprint to investigate how LLMs explore in an open-ended task.
arxiv.org/abs/2501.18009
arxiv.org/abs/2501.18009
Large Language Models Think Too Fast To Explore Effectively
Large Language Models have emerged many intellectual capacities. While numerous benchmarks assess their intelligence, limited attention has been given to their ability to explore, an essential capacit...
arxiv.org
January 31, 2025 at 6:50 PM
Large Language Models can do a lot of things. But do you know they cannot explore effectively, especially in open-ended tasks? Recently, Lan Pan and I dropped a preprint to investigate how LLMs explore in an open-ended task.
arxiv.org/abs/2501.18009
arxiv.org/abs/2501.18009
Just check back in Bluesky and find this is a great place for science threads!
November 21, 2024 at 3:30 PM
Just check back in Bluesky and find this is a great place for science threads!