Tim Baumgรคrtner
@timbmg.bsky.social
๐ค 81
๐ฅ 262
๐ 1
๐จโ๐ป NLP PhD Student
@ukplab.bsky.social
reposted by
Tim Baumgรคrtner
UKP Lab
5 months ago
๐ ๐ช๐ฎ๐ป๐ ๐๐ผ ๐ฒ๐๐ฎ๐น๐๐ฎ๐๐ฒ ๐บ๐ผ๐ฑ๐ฒ๐น๐ ๐ผ๐ป ๐๐ฐ๐ถ๐ฒ๐ป๐๐ถ๐ณ๐ถ๐ฐ ๐ค๐, ๐ฏ๐๐ ๐๐ผ๐๐ฟ ๐ฑ๐ฎ๐๐ฎ๐๐ฒ๐ ๐น๐ฎ๐ฐ๐ธ๐ ๐ฟ๐ฒ๐ฎ๐น-๐๐ผ๐ฟ๐น๐ฑ ๐พ๐๐ฒ๐๐๐ถ๐ผ๐ป๐ ๐ฎ๐๐ธ๐ฒ๐ฑ ๐ฏ๐ ๐ฒ๐ ๐ฝ๐ฒ๐ฟ๐๐? ๐ PeerQA is the solution: a dataset with questions from peer reviews and answers from the original authors. (1/๐งต)
#NLProc
1
2
1
reposted by
Tim Baumgรคrtner
Martin Tutek
7 months ago
๐จ๐จ New preprint ๐จ๐จ Ever wonder whether verbalized CoTs correspond to the internal reasoning process of the model? We propose a novel parametric faithfulness approach, which erases information contained in CoT steps from the model parameters to assess CoT faithfulness.
arxiv.org/abs/2502.14829
loading . . .
Measuring Faithfulness of Chains of Thought by Unlearning Reasoning Steps
When prompted to think step-by-step, language models (LMs) produce a chain of thought (CoT), a sequence of reasoning steps that the model supposedly used to produce its prediction. However, despite mu...
https://arxiv.org/abs/2502.14829
2
46
15
reposted by
Tim Baumgรคrtner
UKP Lab
7 months ago
๐๐ฎ๐ฐ๐-๐๐ต๐ฒ๐ฐ๐ธ๐ถ๐ป๐ด ๐ถ๐ป ๐๐ต๐ฒ ๐๐ด๐ฒ ๐ผ๐ณ ๐๐ โ ๐ ๐ง๐ฎ๐น๐ธ ๐ฏ๐ ๐๐ฟ๐๐ป๐ฎ ๐๐๐ฟ๐ฒ๐๐๐ฐ๐ต @๐๐ ๐ณ๐ผ๐ฟ ๐๐ผ๐ผ๐ฑ Misinformation is a new weapon disrupting public debates, scientific discussions, and political decisions. How can we identify and counter misleading content? (1/๐งต)
loading . . .
Towards real-world fact-checking with large language models
Misinformation poses a growing threat to our society. It has a severe impact on public health by promoting fake cures fear and distrust. Current research
https://aiforgood.itu.int/event/towards-real-world-fact-checking-with-large-language-models/
1
3
1
reposted by
Tim Baumgรคrtner
Florent Daudens
8 months ago
๐ค An Energy Star for AI? Introducing AI Energy Score: First-ever rating system comparing 166 AI models' energy consumption! From LLaMa to Gemma, get transparent โญ๏ธ1-5 efficiency ratings. Incredible work led by
@sashamtl.bsky.social
huggingface.co/blog/sasha/a...
0
25
8
Excited to share that our Paper "PeerQA: A Scientific Question Answering Dataset from Peer Reviews" as been accepted to
#NAACL2025
Looking forward to presenting it in Albuquerque ๐๏ธ!
add a skeleton here at some point
8 months ago
0
5
0
reposted by
Tim Baumgรคrtner
Bertram Hรธjer
10 months ago
What do YOU mean by "intelligence", and does ChatGPT fit your definition? We collected the major criteria used in CogSci and other fields, and designed a survey to find out! Access link:
www.survey-xact.dk/collect
Code: 4S7V-SN4M-S536 Time: 5-10 mins
loading . . .
Perspectives on Intelligence: Community Survey
Research survey exploring how NLP/ML/CogSci researchers define and use the concept of intelligence.
https://bertramhojer.github.io/projects/intelligence-survey/
2
32
23
you reached the end!!
feeds!
log in