5 papers
Tracing Uncertainty in Language Model "Reasoning"
Nils Grünefeld, Bertram Højer, Philipp Mondorf +5
Language model (LM) "reasoning", commonly described as Chain-of-Thought or test-time scaling, often improves benchmark performance, but the dynamics underlying this process remain…
Language Models Learn Universal Representations of Numbers and Here's Why You Should Care
Michal Å tefánik, Timothee Mickus, Marek KadlÄÃk +7
Prior work has shown that large language models (LLMs) often converge to accurate input embedding for numbers, based on sinusoidal representations. In this work, we quantify that t…
On the Notion that Language Models Reason
Bertram Højer
Language models (LMs) are said to be exhibiting reasoning, but what does this entail? We assess definitions of reasoning and how key papers in the field of natural language process…
Research Community Perspectives on "Intelligence" and Large Language Models
Bertram Højer, Terne Sasha Thorn Jakobsen, Anna Rogers +1
Despite the widespread use of ''artificial intelligence'' (AI) framing in Natural Language Processing (NLP) research, it is not clear what researchers mean by ''intelligence''. To…
Improving Reasoning Performance in Large Language Models via Representation Engineering
Bertram Højer, Oliver Jarvis, Stefan Heinrich
Recent advancements in large language models (LLMs) have resulted in increasingly anthropomorphic language concerning the ability of LLMs to reason. Whether reasoning in LLMs shoul…