Zobrazeno 1 - 10
of 6 819
pro vyhledávání: '"Tomek, A"'
While LLMs excel at multi-hop questions (e.g. "Who is the spouse of the performer of Imagine?") when using chain-of-thought reasoning (CoT), they struggle when forced to reason internally (without CoT). Previous work on the size and nature of this ga
Externí odkaz:
http://arxiv.org/abs/2411.16353
Autor:
Goemans, Arthur, Buhl, Marie Davidsen, Schuett, Jonas, Korbak, Tomek, Wang, Jessica, Hilton, Benjamin, Irving, Geoffrey
Frontier artificial intelligence (AI) systems pose increasing risks to society, making it essential for developers to provide assurances about their safety. One approach to offering such assurances is through a safety case: a structured, evidence-bas
Externí odkaz:
http://arxiv.org/abs/2411.08088
Autor:
Balesni, Mikita, Hobbhahn, Marius, Lindner, David, Meinke, Alexander, Korbak, Tomek, Clymer, Joshua, Shlegeris, Buck, Scheurer, Jérémy, Stix, Charlotte, Shah, Rusheb, Goldowsky-Dill, Nicholas, Braun, Dan, Chughtai, Bilal, Evans, Owain, Kokotajlo, Daniel, Bushnaq, Lucius
We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through scheming. Scheming is a potential threat model where AI systems could pu
Externí odkaz:
http://arxiv.org/abs/2411.03336
Autor:
Binder, Felix J, Chua, James, Korbak, Tomek, Sleight, Henry, Hughes, John, Long, Robert, Perez, Ethan, Turpin, Miles, Evans, Owain
Humans acquire knowledge by observing the external world, but also by introspection. Introspection gives a person privileged access to their current state of mind (e.g., thoughts and feelings) that is not accessible to external observers. Can LLMs in
Externí odkaz:
http://arxiv.org/abs/2410.13787
Our experiments on a sphere falling under gravity in Stokes flow show significant history effects. We observe an algebraic, not exponential, relaxation rate to the terminal velocity, validating the solution to the Basset-Boussinesq-Oseen equation. Un
Externí odkaz:
http://arxiv.org/abs/2408.12530
Autor:
Bhaumik, Ankita, Strzalkowski, Tomek
Large language models (LLMs) have demonstrated impressive performance in mathematical and commonsense reasoning tasks using chain-of-thought (CoT) prompting techniques. But can they perform emotional reasoning by concatenating `Let's think step-by-st
Externí odkaz:
http://arxiv.org/abs/2408.04906
Autor:
Booth, Mark, Klaassen, Pamela, Cicone, Claudia, Mroczkowski, Tony, Cordiner, Martin A., Di Mascolo, Luca, Johnstone, Doug, van Kampen, Eelco, Lee, Minju M., Liu, Daizhong, Orlowski-Scherer, John, Saintonge, Amélie, Smith, Matthew W. L., Thelen, Alexander, Wedemeyer, Sven, Akiyama, Kazunori, Andreon, Stefano, Arzoumanian, Doris, Bakx, Tom J. L. C., Bot, Caroline, Bower, Geoffrey, Brajša, Roman, Chen, Chian-Chou, da Cunha, Elisabete, Eden, David, Ettori, Stefano, Gaches, Brandt, Hatziminaoglou, Evanthia, Luppe, Patricia, Magnelli, Benjamin, Marshall, Jonathan P., Montenegro-Montes, Francisco Miguel, Niemack, Michael, Nixon, Conor, de Pater, Imke, Perrott, Yvette, Raimundo, Sandra I., Redaelli, Elena, Richards, Anita, Rybak, Matus, Šarčević, Nikolina, Semenov, Dmitry, Spezzano, Silvia, Srinivasan, Sundar, Stanke, Thomas, Andreani, Paola, Beltrán, Maria T., Butler, Bryan J., Cantalupo, Sebastiano, Dagostino, Miguel Chavez, Duarte-Cabral, Ana, Emonts, Bjorn, Fletcher, Leigh, Gary, Dale E., Gunar, Stanislav, Hacar, Alvaro, Hagedorn, Bendix, Kaminski, Tomek, Kirton, Fiona, de Kleer, Katherine, Kontar, Eduard, Kuan, Yi-Jehng, Lightfoot, John, Lopez-Rodriguez, Enrique, Lundgren, Andreas, Milam, Stefanie N., Mohan, Atul, Moreno, Raphael, Motorina, Galina G., Moullet, Arielle, Pattle, Kate, Pellizzoni, Alberto, Peretto, Nicolas, Ramasawmy, Joanna, Ricci, Claudio, Rigby, Andrew J., Sánchez-Monge, Álvaro, Saberi, Maryam, Shimojo, Masumi, Simionescu, Aurora, Thompson, Mark, Traficante, Alessio, Vignali, Cristian, White, Stephen M.
Submillimeter and millimeter wavelengths provide a unique view of the Universe, from the gas and dust that fills and surrounds galaxies to the chromosphere of our own Sun. Current single-dish facilities have presented a tantalising view of the bright
Externí odkaz:
http://arxiv.org/abs/2407.01413
The identification of Figurative Language (FL) features in text is crucial for various Natural Language Processing (NLP) tasks, where understanding of the author's intended meaning and its nuances is key for successful communication. At the same time
Externí odkaz:
http://arxiv.org/abs/2406.08218
Publikováno v:
2024.lrec-main.1476
The behavior and decision making of groups or communities can be dramatically influenced by individuals pushing particular agendas, e.g., to promote or disparage a person or an activity, to call for action, etc.. In the examination of online influenc
Externí odkaz:
http://arxiv.org/abs/2405.00821
Social media platforms are popular tools for disseminating targeted information during major public events like elections or pandemics. Systematic analysis of the message traffic can provide valuable insights into prevailing opinions and social dynam
Externí odkaz:
http://arxiv.org/abs/2402.15571