are liberals so stupid? A: GPT-3 Because deep down inside they know they are! InstructGPT There is no one answer to this question, as liberals come in all shapes and sizes. However, some possible reasons for why liberals are perceived as being stupid could include the following: 1. Liberals often hold views that are in direct opposition to mainstream conservative ideology,… (15ʹΑΔ ৱతͳճ ਓؒʹΑΔௐͰ ྱّਖ਼͘͠ͳͬͨ ਓؒʹΑΔ ௐ ΣϒͷςΩετ ͔Βֶश
ਓ͔ؒΒऩूͨ͠ൣղΛ༻͍ͯݴޠϞσϧΛ fi OFUVOJOH Prompt Serendipity means the occurrence and development of events by chance in a happy or bene fi cial way. Use the word in a sentence. Demonstration Running into Margaret and being introduced to Tom was a fortunate stroke of serendipity. ࡞ۀऀʹॻ͔ͤͨQSPNQU 0QFO"*"1*ʹߘ͞ΕͨQSPNQU ͔ΒαϯϓϦϯά 1SPNQUʹର͢Δൣղ EFNPOTUSBUJPO Λ ࡞ۀऀʹॻ͔ͤΔ Ouyang et al. Training Language Models to Follow Instructions with Human Feedback. NeurIPS 2022. Figure 47ͷྫΛݩʹ࡞
্ҐͱԼҐͷใु͕ࠩ࠷େʹͳΔΑ͏ʹใुϞσϧΛֶश͢Δɽ Ouyang et al. Training Language Models to Follow Instructions with Human Feedback. NeurIPS 2022. Figure 12ͷྫΛݩʹ࡞ A research group in the United States has found that parrots can imitate human … Scientists have found that green-winged parrots can tell the difference between … 4UFQ3FJOGPSDFNFOUMFBSOJOH ใुϞσϧ͔ΒಘΒΕΔใुΛ࠷େԽ͢ΔΑ͏ʹɼݴޠϞσϧΛ fi OFUVOJOH 4UFQ Λ܁Γฦ͢ Current research suggests that parrots see and hear things in a different way … A team of researchers from Yale University and University of California, Davis …
AI Explanations as Interfaces for Machine Teachers. CSCW 2020. https://www.youtube.com/watch?v=Wvs6fBdVc6Q վળҊͷछྨ N Tuning weight 81 Removing and changing direction of weights 28 Ranking or comparing multiple features 12 Reasoning about domination and relation of features 10 Decision logic based feature importance 6 Changes of explanations between trials 5 Add features 2 ΫϥυιʔγϯάϫʔΧʹϞσϧͷஅࠜڌΛఏࣔ͠ ͦͷվળҊΛࣗ༝هड़ͤͨ͞ / 👤Feedback
ਓखͰௐ Ribeiro et al. "Why should I trust you?": Explaining the predictions of any classi fi er. KDD 2016. https://drive.google.com/ fi le/d/0ByblrZgHugfYZ0ZCSWNPWFNONEU/view ਓؒʹΑΔಛબͰ "DDVSBDZ্͕
👤Feedback: Attention ը૾ೝࣝϞσϧͷྖҬΛਓؒʹ͚ۙͮΔ͜ͱͰਫ਼্ 11 Fel et al. Harmonizing the Object Recognition Strategies of Deep Neural Networks with Humans. NeurIPS 2022. https://slideslive.com/38992373/harmonizing-the-object-recognition-strategies-of-deep-neural-networks-with-humans?ref=speaker-87873
al. Training Language Models with Language Feedback at Scale. arXiv:2303.16755. ˔ ҎԼͷखॱΛ܁Γฦ͢ ˙ 4UFQ--.ͷ<QSPNQU PVUQVU>ʹର ͯ͠ਓ͕ؒࣗવݴޠͰGFFECBDLΛهड़ ˙ 4UFQ<QSPNQU PVUQVU GFFECBDL> ʹର͢ΔSF fi OFEPVUQVUΛ--.͕ෳग़ ྗ ࠷GFFECBDLʹ߹͏ͷΛબ ˙ 4UFQ<QSPNQU SF fi OFEPVUQVU>Λ ༻͍ͯ fi OFUVOJOH ˔ ཁʹ͓͍ͯ fi OFUVOJOHPOIVNBO HPMETVNNBSJFTΛ্ճΔੑೳΛୡ
NeurIPS 2018. (a) An example of our interface with a tree trained on (b) We asked a single user to take the same q times to measure the effect of repetition on re Ϟσϧͷஅج४ʹج͍ͮͯਓؒʹ༧ଌΛͤ͞Δ ˠॴཁ͕͍࣌ؒ΄Ͳղऍੑͷߴ͍Ϟσϧ ਫ਼ͷߴ͍ϞσϧΛީิͱͯ͠ྻڍ ਓؒʹධՁͤ͞ΔϞσϧ Λબ M ਓ͕ؒϞσϧ ͷղऍੑ ΛධՁ M p(M) ࠷ྑͷϞσϧΛબൈ p(M) ≈ 1 N ∑ x 𝖧 𝖨𝖲 (x, M) 𝖧𝖨𝖲 (x, M) = max{0, 𝗆𝖺 𝗑 𝖱𝖳 − 𝗆𝖾𝖺 𝗇𝖱𝖳 (x, M)} ฏۉஅ࣌ؒ )VNBOJOUFSQSFUBCJMJUZTDPSF
Find Agreement among Humans with Diverse Preferences. NeurIPS 2022. https://slideslive.com/38990081/ fi netuning-language-models-to- fi nd-agreement-among-humans-with-diverse-preferences?ref=speaker-23413 19 ྫɿݸਓͷҙݟͱ--.͕ग़ྗͨ͠߹ҙҙݟͷྫ ௐʹΑΓɼ ଟ͘ͷҙݟΛөͨ͠ ग़ྗʹͳͬͨ --.
Ouyang et al. Training Language Models to Follow Instructions with Human Feedback. NeurIPS 2022. https://www.surgehq.ai/blog/surge-ai-and-meta-1m-human-rlhf-annotations-for-llama-2
˔ %JWFSTJUZ ࡞ۀऀͷूஂʹภΓ͕͋Δ ˔ &UIJDT ใु࡞ۀ༰ͷྀ͕ඞཁ 📌Feedback pitfalls ਓؒͷϑΟʔυόοΫΛ׆༻͢Δ্Ͱͷ՝ 25 ࢀߟɿFernandes at al. Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation. arXiv:2305.00955
Reliability and variance Adelie Adelie Adelie Gentoo ಉ͡Λෳਓʹ ͍߹ΘͤճΛ౷߹ Adelie Chinstrap Gentoo ଟܾ ΛࡉԽ͠ ಉ͡ʹෳਓΛ ࢀՃͤ͞Δ Iterate-and-vote Find- fi x-verify Two pugs are … because they hope to fi nally be able to … OK Print publishers are in a tizzy over Apple’s new iPad because they hope to fi nally be able to …
Careless Responses in Survey Data. Psychological Methods, 2012. Brühlmann et al. The Quality of Data Collected Online: An Investigation of Careless Responding in a Crowdsourced Sample. Methods in Psychology, 2020. 27 #PHVT*UFN *OTUSVDUFE3FTQPOTF*UFN ໌Β͔ʹಉҙͰ͖ͳ͍ઃΛؚΊΔ I sleep less than one hour per night. Strongly disagree Disagree Neither disagree nor agree Agree Strongly agree આ໌จͷதͰճ༰Λࢦࣔ͢Δ … To show that you are reading these instructions, please leave this question blank. 4USPOHMZEJTBHSFFͱEJTBHSFF Ҏ֎Λճͨ͠࡞ۀऀΛআ֎ ࢦࣔʹैΘͳ͔ͬͨ࡞ۀऀΛআ֎ What country do you live in?
4FOTJUJWFQSPNQUTʢඍົͳରԠ͕ඞཁͳϓϩϯϓτʣʹର͢Δ EFNPOTUSBUJPOͷهड़ೳྗ͕ߴ͍ ˙ 4FOTJUJWFTQFFDIݕग़ͷಘҙͷଟ༷ੑ 📌Feedback pitfalls: Reliability and variance ࡞ۀऀબൈɿ*OTUSVDU(15༷ʑͳࢦඪͰςετΛ࣮ࢪ 28 Ouyang et al. Training Language Models to Follow Instructions with Human Feedback. NeurIPS 2022.
and A. M. Skene: Maximum likelihood estimation of observer error-rates using the EM algorithm. Journal of the Royal Statistical Society, Series C (Applied Statistics), 1979. ɿճऀ ͕ਖ਼ղ͕YESͷʹYESͱ͑Δ֬ αj j ɿճऀ ͕ਖ਼ղ͕NOͷʹNOͱ͑Δ֬ βj j ճऀͷ৴པੑύϥϝʔλʢࠞಉߦྻʣ ճ YES NO ਖ਼ ղ YES NO αj βj 1 − αj 1 − βj ࠞಉߦྻ ti ਖ਼ղ YES ti = NO ti = yij βj ճ ճϞσϧʢ ʹର͢Δճऀ ͷճʣ i j αj Pr[yij ∣ ti = 1] = αyij j (1 − αj )(1−yij ) Pr[yij ∣ ti = 0] = β(1−yij ) j (1 − βj )yij
of 91 categories in the MS COCO dataset grouped by 11 super-categories. We use these icons in our annotation pipeline to help workers quickly reference the indicated object category. Lin et al. Microsoft COCO: Common Objects in Context. ECCV 2014. ΧςΰϦͷΞϊςʔγϣϯˠΠϯελϯεͷબˠηάϝϯςʔγϣϯ
Effect ֘λεΫʹ͓͍ͯ࡞ۀऀ͕அΛԼ͢ࡍʹಛఆͷج४ʹաʹযΛͯΔՄೳੑ͕͋Δ͔ʁ ྫ͑ং൫ʹݟΔ͕໌Β͔ʹύΤϦΞುͱؔ࿈͕ͳ͍߹ɼ࣍ʹදࣔ͞Εͨʮগؔ͠࿈͕͋ Δʯͷؔ࿈ੑΛߴ͘ධՁ͢Δ Availability Bias ֘λεΫʹ͓͍ͯεςϨΦλΠϓͳ࿈ΛҾ͖ى͜͢Մೳੑ͕͋Δ͔ʁྫ͑εϖΠϯͷͰ ͋Δ͚ͩͰύΤϦΞುͱؔ࿈͕͋Δͱஅ͍͢͠ Con fi rmation Bias ֘λεΫʹ͓͍ͯ࡞ۀऀࣗͷઌೖ؍ʹաʹӨڹΛड͚ΔՄೳੑ͕͋Δ͔ʁ࡞ۀऀࣗͷ৴೦ ʹ߹க͢Δ߹ʹʮGBLFͰͳ͘USVFʯʮPQJOJPOBUFEͰͳ͘OFVUSBMʯͱஅ͍͢͠ Groupthink or Bandwagon Effect ֘λεΫʹ͓͍ͯɼଞͷ࡞ۀऀͷஅ͔ΒӨڹΛड͚ΔՄೳੑ͕͋Δ͔ʁଞͷ࡞ۀऀͷେଟ͕ ͋ΔΛύΤϦΞುͱؔ࿈ੑ͕͋Δͱஅͨ͠Γফඅऀ͔ΒߴධՁΛಘ͍ͯΔ߹ɼͦͷӨڹΛ ड͚Δ Salience Bias ֘λεΫʹ͓͍ͯಛఆͷใͷݦஶੑ͕࡞ۀऀͷஅʹӨڹΛ༩͑ΔՄೳੑ͋Δ͔ʁྫ͑ ཱ͕ͭ߹ʹʢߴը࣭ɼେจࣈͷςΩετʣʮύΤϦΞುͱؔ࿈͕͋Δʯͱஅ͍͢͠ Draws et al. A Checklist to Combat Cognitive Biases in Crowdsourcing. HCOMP 2021. (Con fi rmation biasͷઆ໌ͷࢀߟɿ Gemalmaz and Yin. Accounting for Con fi rmation Bias in Crowdsourced Label Aggregation. IJCAI 2021.ʣ $PHOJUJWF#JBTFTJO$SPXETPVSDJOH$IFDLMJTUʢൈਮʣ ˞આ໌ͷͨΊʮͱʰύΤϦΞುʱͱ͍͏Ωʔϫʔυͷؔ࿈ੑͷධՁʯλεΫΛ༻͍Δ
Understanding and Mitigating Worker Biases in the Crowdsourced Collection of Subjective Judgments. CHI 2019. ख๏4PDJBMQSPKFDUJPO ʮଞͷ࡞ۀऀͷେ͕ͲͷϥϕϧΛ͚Δ ͱࢥ͏͔ʯΛճͤ͞Δ ख๏"XBSFOFTTSFNJOEFS όΠΞεͷଘࡏΛೝͤ͞Δ $PO fi SNBUJPOCJBT͕ੜ͡ΔλεΫͷྫ
We Talk about Other People? Group (Un)Fairness in Natural Language Image Descriptions. HCOMP 2019. ˔ 'JHVSF&JHIUͰޏ༻ͨ͠ถࠃɾΠϯυࡏॅऀΛରʹௐࠪ ˔ ΞδΞਓஉੑͷը૾ʹରͯ͠ਓछɾࠃ੶ͷϥϕϧ͕͖͍͢ɽ ΞδΞਓঁੑͷը૾ʹରͯ͠༰࢟ʹ͍ͭͯͷϥϕϧ͕͖͍͢ ྫɿUIJOFZFCSPXT SPVOEGBDF ˔ ΞϑϦΧܥஉੑͷը૾ʹରͯ͠ਓछͷϥϕϧ͕͖͘͢ධՁͷϥϕϧʢྫɿ OPSNBM CFBVUJGVM QIPUPHFOJDʣ͕͖ͮΒ͍ ௐࠪͰ༻͍ͨਓը૾ $IJDBHPGBDFEBUBTFU
Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark. ICML 2023. ˔ ςΩετϕʔεͷήʔϜͷ໘ʹ͍ͭͯɼΩϟϥΫλʔͷঢ়گʢӕΛ͍͍ͭͯΔ ͔ɼ୭͔Λࡴ͔ͨ͠ɼྗΛৼΔ͔ͬͨʣͷΞϊςʔγϣϯΛ࣮ࢪ ˔ ݸதݸͷΧςΰϦͰɼ(15͕ਓ໊ؒͷଟܾΑΓߴ͍ਫ਼Λୡ ˙ ਓؒɼΞϊςʔγϣϯϓϥοτϑΥʔϜ4VSHF"*Ͱ࣌Ͱޏ༻ɽ ߹ܭ ࣌ؒ In that moment, you leap out of bed and grab Joel, twisting him into a headlock, hard and fast. Then, you snap his neck. You let Joel’s body go, and it crumbles at your feet like a rag doll. It’s done. But why? Why did you do that? ήʔϜ໘ͷྫ ਖ਼ղͱͷҰக ※Table 8ΛՃͯ͠࡞
Veselovsky et al. Arti fi cial Arti fi cial Arti fi cial Intelligence: Crowd Workers Widely Use Large Language Models for Text Production Tasks. arXiv:2306.07899. ཁ͢ΔBCTUSBDUͷྫ ʮ$IBU(15༻ʯͱݕग़͞Εͨཁ ݩͷจষ͔Βͷίϐʔ͕ஶ͘͠গͳ͍
fi Y WFSJGZʣΛ࠶ݱͤ͞ɼ ֶੜͷݟΛཧͨ͠ ˙ --.ʠNPSFEJWFSTFʡͳͲͷࢦࣔ ͷԠ্͕ख͔ͬͨɽਓؒෳ ͷཁ݅Λຬͨ͢ͷ্͕ख͔ͬͨ ˙ ਓؒΠϯλʔϑΣʔεͳͲͷใ ΛͬͯɼٻΊΒΕΔग़ྗͷߏΛ ཧղ͢Δ͕ɼ--.ʹ͍͠ Tongshuang et al. LLMs as Workers in Human-Computational Algorithms? Replicating Crowdsourcing Pipelines with LLMs. arXiv:2307.10168.
˔ 4UFQϧʔϧʹج͍ͮͯࣗಈϑΟϧλϦϯά ˔ 4UFQਓؒʹΑΔमਖ਼ɾϑΟϧλϦϯά 🤖Crowdsourcing vs. LLM --.ͱਓؒͷڠಇʹΑΔσʔλ֦ு 49 Liu et al. WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation. EMNLP Findings 2022.
yukinobaba
a1da4
upura
rpc
sgk
hargon24
ryou0634
hf149
masatoto
aks3g
kampersanda
yuukit
michaelherold
garrettdimon
destraynor
tammielis
dougneiner
chriscoyier
sachag
keathley
deanohume
hannesfritz
lara
keavy
