Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Zelikman, Eric"'
Autor:
Fränken, Jan-Philipp, Zelikman, Eric, Rafailov, Rafael, Gandhi, Kanishk, Gerstenberg, Tobias, Goodman, Noah D.
When prompting a language model (LM), users often expect the model to adhere to a set of behavioral principles across diverse tasks, such as producing insightful content while avoiding harmful or biased language. Instilling such principles (i.e., a c
Externí odkaz:
http://arxiv.org/abs/2404.14313
When writing and talking, people sometimes pause to think. Although reasoning-focused works have often framed reasoning as a method of answering questions or completing agentic tasks, reasoning is implicit in almost all written text. For example, thi
Externí odkaz:
http://arxiv.org/abs/2403.09629
Autor:
Zelikman, Eric, Ma, Wanjing Anya, Tran, Jasmine E., Yang, Diyi, Yeatman, Jason D., Haber, Nick
Developing an educational test can be expensive and time-consuming, as each item must be written by experts and then evaluated by collecting hundreds of student responses. Moreover, many tests require multiple distinct sets of questions administered
Externí odkaz:
http://arxiv.org/abs/2310.06837
Several recent advances in AI systems solve problems by providing a "scaffolding" program that structures multiple calls to language models (LMs) to generate better outputs. A scaffolding program is written in a programming language such as Python. I
Externí odkaz:
http://arxiv.org/abs/2310.02304
Referenceless metrics (e.g., CLIPScore) use pretrained vision--language models to assess image descriptions directly without costly ground-truth reference texts. Such methods can facilitate rapid progress, but only if they truly align with human pref
Externí odkaz:
http://arxiv.org/abs/2309.11710
Inductive reasoning is a core problem-solving capacity: humans can identify underlying principles from a few examples, which robustly generalize to novel scenarios. Recent work evaluates large language models (LLMs) on inductive reasoning tasks by di
Externí odkaz:
http://arxiv.org/abs/2309.05660
In recent years, deep learning-based solar forecasting using all-sky images has emerged as a promising approach for alleviating uncertainty in PV power generation. However, the stochastic nature of cloud movement remains a major challenge for accurat
Externí odkaz:
http://arxiv.org/abs/2306.11682
Language model training in distributed settings is limited by the communication cost of gradient exchanges. In this short note, we extend recent work from Malladi et al. (2023), using shared randomness to perform distributed fine-tuning with low band
Externí odkaz:
http://arxiv.org/abs/2306.10015
Language models often achieve higher accuracy when reasoning step-by-step in complex tasks. However, even when arriving at a correct final answer, their rationales are often logically unsound or inconsistent. This is a major issue when reliable reaso
Externí odkaz:
http://arxiv.org/abs/2306.04031
Token embeddings, a mapping from discrete lexical symbols to continuous vectors, are at the heart of any language model (LM). However, lexical symbol meanings can also be determined and even redefined by their structural role in a long context. In th
Externí odkaz:
http://arxiv.org/abs/2305.16349