Exploring the latent space of human experience. Here to meet cool people and share my findings. Follow to see cool NLP papers #Psychology #AI #OpenScience #NLPhttps://bsky.app/profile/hplisiecki.bsky.socialhttps://bsky.app/profile/hplisiecki.bsky.social/post/3mldvzog7gk2jThe primary dimension of psychometric difference in LLMs is phenomenological - the extent to which they respond as if they had internal, phenomenal experience. #AI #LLM #Psychometrics arxiv.org/abs/2605.05080 https://arxiv.org/abs/2605.0508008 May 2026 14:13 +0000at://did:plc:p6jdnthegit2r5e4kw27uaay/app.bsky.feed.post/3mldvzog7gk2jhttps://bsky.app/profile/hplisiecki.bsky.social/post/3mfvzcy53e22iOnline surveys are on their way to the grave. Are we working on alternatives? Is it time to start proctoring every survey taker? https://www.nature.com/articles/d41586-026-00386-228 Feb 2026 10:28 +0000at://did:plc:p6jdnthegit2r5e4kw27uaay/app.bsky.feed.post/3mfvzcy53e22ihttps://bsky.app/profile/hplisiecki.bsky.social/post/3mfvytnweqk2yComputational Psycholinguistics discord server is an experimental research square for people working on the cross-section of NLP and Psychology to connect, discuss ideas, learn from each other, and pick up collaborators. You can join by following the link below discord.gg/2DUHmcnY6Z https://discord.gg/2DUHmcnY6Z28 Feb 2026 10:20 +0000at://did:plc:p6jdnthegit2r5e4kw27uaay/app.bsky.feed.post/3mfvytnweqk2yhttps://bsky.app/profile/hplisiecki.bsky.social/post/3mf3w5fbj3s2zCurrent main bandwagon in AI x Psychology research has been embedding questionnaires with transformers. Are we ready to answer the question of whether transformers actually uncover the latent psychological dimensions vs. they are just useful in pinpointing any text differences?18 Feb 2026 01:22 +0000at://did:plc:p6jdnthegit2r5e4kw27uaay/app.bsky.feed.post/3mf3w5fbj3s2zhttps://bsky.app/profile/hplisiecki.bsky.social/post/3m4tnxdyxl22mProud to share what I've been working on for the last half a year - a method to statistically assess and explain differences in the perceived meaning of concepts based on small samples. Allow me to introduce the Supervised Semantic Differential https://osf.io/preprints/psyarxiv/gvrsb_v104 Nov 2025 23:13 +0000at://did:plc:p6jdnthegit2r5e4kw27uaay/app.bsky.feed.post/3m4tnxdyxl22mhttps://bsky.app/profile/hplisiecki.bsky.social/post/3lkw5sncvxc2yFor all #Severance fans out there. Baldwin, A. L. (1942). Personal structure analysis: A statistical method for investigating the single personality. The Journal of Abnormal and Social Psychology, 37(2), 163–183. https://doi.org/10.1037/h006169721 Mar 2025 21:28 +0000at://did:plc:p6jdnthegit2r5e4kw27uaay/app.bsky.feed.post/3lkw5sncvxc2yhttps://bsky.app/profile/hplisiecki.bsky.social/post/3lijp2gu6ls2kResearchers have to realize the risks of using black box models and take robust measures to strengthen the validity of their conclusions. Our Paper "𝗛𝗶𝗴𝗵 𝗿𝗶𝘀𝗸 𝗼𝗳 𝗽𝗼𝗹𝗶𝘁𝗶𝗰𝗮𝗹 𝗯𝗶𝗮𝘀 𝗶𝗻 𝗯𝗹𝗮𝗰𝗸 𝗯𝗼𝘅 𝗲𝗺𝗼𝘁𝗶𝗼𝗻 𝗶𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲 𝗺𝗼𝗱𝗲𝗹𝘀" has just been published in Scientific Reports19 Feb 2025 11:42 +0000at://did:plc:p6jdnthegit2r5e4kw27uaay/app.bsky.feed.post/3lijp2gu6ls2khttps://bsky.app/profile/hplisiecki.bsky.social/post/3lc23gclrt22nSo.. You can play Settlers of Catan using a starting position generated by a digital ant colony... And it's gonna be super balanced.. https://www.researchgate.net/publication/344758433_Using_Ant_Colony_Optimisation_for_map_generation_and_improving_game_balance_in_the_Terra_Mystica_and_Settlers_of_Catan_board_games28 Nov 2024 22:10 +0000at://did:plc:p6jdnthegit2r5e4kw27uaay/app.bsky.feed.post/3lc23gclrt22nhttps://bsky.app/profile/hplisiecki.bsky.social/post/3lbz4nx4a6s2yNew BSky Update: fake accounts @jaceksutryk.bsky.social is an account of "supposedly" the president of Polish city Wroclaw, which added me here just after I posted my handle to one of Polish political shitposting groups. Beware who you follow. The high trust society we are building might backfire.28 Nov 2024 12:59 +0000at://did:plc:p6jdnthegit2r5e4kw27uaay/app.bsky.feed.post/3lbz4nx4a6s2yhttps://bsky.app/profile/hplisiecki.bsky.social/post/3lbqaesjqls2sIt's obviously true that humans are biased - otherwise m there would be no bias in ML models. More so, in some cases the latter bias is even recommended. But in most cases an unbiased model is what we want. Read more to know when bias is a feature, and when it is a bug. 🧶🐈25 Nov 2024 00:12 +0000at://did:plc:p6jdnthegit2r5e4kw27uaay/app.bsky.feed.post/3lbqaesjqls2shttps://bsky.app/profile/hplisiecki.bsky.social/post/3lbk5ki6bb22n1/ 🚨 Introducing Semantic Blinding 🚨 What if AI could analyze text without inheriting biases from its training data? Enter Semantic Blinding, a novel method to remove biases like political or gender bias in sentiment analysis. Here’s how it works: 🧵22 Nov 2024 14:05 +0000at://did:plc:p6jdnthegit2r5e4kw27uaay/app.bsky.feed.post/3lbk5ki6bb22nhttps://bsky.app/profile/hplisiecki.bsky.social/post/3lbk3egeops2uBudapest is an amazing city (and has a lot of my favorite Art Nouveau architectural diamonds like the Párisi Udvar seen on the pictures) It was a pleasure to take part in the 2nd Budapest Methods Workshop on LLMs. Thanks @miklossebok.bsky.social for invitation ;)22 Nov 2024 13:26 +0000at://did:plc:p6jdnthegit2r5e4kw27uaay/app.bsky.feed.post/3lbk3egeops2uhttps://bsky.app/profile/hplisiecki.bsky.social/post/3lbhcu6lbos2zIm gonna try to jumpstart a little Natural Language Processing Psychology community because I think this take on Psych needs more visibility. Comment if you want to be added, or removed 😉 https://bsky.app/profile/did:plc:p6jdnthegit2r5e4kw27uaay/lists/3lbhb3ss3622l [contains quote post or other embedded content]21 Nov 2024 11:02 +0000at://did:plc:p6jdnthegit2r5e4kw27uaay/app.bsky.feed.post/3lbhcu6lbos2zhttps://bsky.app/profile/hplisiecki.bsky.social/post/3lbemfaxtak2cEXTREMELY Excited to share my latest preprint "Bias Free Sentiment Analysis" where i have solved the problem of bias in deep learning SA models. Using the principle of semantic blinding I construct the Semantic Propagation Graph Neural Network which makes predictions based on... 1/n20 Nov 2024 09:15 +0000at://did:plc:p6jdnthegit2r5e4kw27uaay/app.bsky.feed.post/3lbemfaxtak2chttps://bsky.app/profile/hplisiecki.bsky.social/post/3lbb4dytozk2jExtended bio: I make AI tools for psychologists and sometimes manage to even whip up a theoretical contribution. Currently finishing my PhD in emotion research. My other projects are mainly meta-scientific and revolve around bias detection and scientific excellence.18 Nov 2024 23:50 +0000at://did:plc:p6jdnthegit2r5e4kw27uaay/app.bsky.feed.post/3lbb4dytozk2jhttps://bsky.app/profile/hplisiecki.bsky.social/post/3lbansh4syc27If you could take one memory with you to the "whatever happens after we die place" (including the total void and nothingness option), what would it be? Memory size limit - one second.18 Nov 2024 19:29 +0000at://did:plc:p6jdnthegit2r5e4kw27uaay/app.bsky.feed.post/3lbansh4syc27https://bsky.app/profile/hplisiecki.bsky.social/post/3lbajzwbc6m2nFrom my recent research on vector representation of emotions: PCA on emotion vectors recovers the classical dimensions of affect (valence, arousal etc.)18 Nov 2024 18:22 +0000at://did:plc:p6jdnthegit2r5e4kw27uaay/app.bsky.feed.post/3lbajzwbc6m2n