7 papers
Characterizing Pattern Matching and Its Limits on Compositional Task Structures
Hoyeon Chang, Jinho Park, Hanseul Cho +7
Despite impressive capabilities, LLMs' successes often rely on pattern-matching behaviors, yet these are also linked to OOD generalization failures in compositional tasks. However,…
Reasoning Models Better Express Their Confidence
Dongkeun Yoon, Seungone Kim, Sohee Yang +6
Despite their strengths, large language models (LLMs) often fail to communicate their confidence accurately, making it difficult to assess when they might be wrong and limiting the…
Latent Reasoning via Sentence Embedding Prediction
Hyeonbin Hwang, Byeongguk Jeon, Seungone Kim +7
Autoregressive language models (LMs) generate one token at a time, yet human reasoning operates over higher-level abstractions - sentences, propositions, and concepts. This contras…
Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?
Sohee Yang, Nora Kassner, Elena Gribovskaya +2
We evaluate how well Large Language Models (LLMs) latently recall and compose facts to answer multi-hop queries like "In the year Scarlett Johansson was born, the Summer Olympics w…
Do Large Language Models Latently Perform Multi-Hop Reasoning?
Sohee Yang, Elena Gribovskaya, Nora Kassner +2
We study whether Large Language Models (LLMs) latently perform multi-hop reasoning with complex prompts such as "The mother of the singer of 'Superstition' is". We look for evidenc…
How Do Large Language Models Acquire Factual Knowledge During Pretraining?
Hoyeon Chang, Jinho Park, Seonghyeon Ye +4
Despite the recent observation that large language models (LLMs) can store substantial factual knowledge, there is a limited understanding of the mechanisms of how they acquire fac…