Zobrazeno 1 - 10
of 355
pro vyhledávání: '"Jurafsky, Dan"'
Autor:
Wu, Zhengxuan, Arora, Aryaman, Geiger, Atticus, Wang, Zheng, Huang, Jing, Jurafsky, Dan, Manning, Christopher D., Potts, Christopher
Fine-grained steering of language model outputs is essential for safety and reliability. Prompting and finetuning are widely used to achieve these goals, but interpretability researchers have proposed a variety of representation-based techniques as w
Externí odkaz:
http://arxiv.org/abs/2501.17148
Autor:
Suzgun, Mirac, Gur, Tayfun, Bianchi, Federico, Ho, Daniel E., Icard, Thomas, Jurafsky, Dan, Zou, James
As language models (LMs) become integral to fields like healthcare, law, and journalism, their ability to differentiate between fact, belief, and knowledge is essential for reliable decision-making. Failure to grasp these distinctions can lead to sig
Externí odkaz:
http://arxiv.org/abs/2410.21195
In-context learning (ICL) is a powerful technique for getting language models to perform complex tasks with no training updates. Prior work has established strong correlations between the number of in-context examples provided and the accuracy of the
Externí odkaz:
http://arxiv.org/abs/2410.16531
Large language models (LLMs) have shown high agreement with human raters across a variety of tasks, demonstrating potential to ease the challenges of human data collection. In computational social science (CSS), researchers are increasingly leveragin
Externí odkaz:
http://arxiv.org/abs/2408.15204
Autor:
de la Fuente, Antón, Jurafsky, Dan
This study asks how self-supervised speech models represent suprasegmental categories like Mandarin lexical tone, English lexical stress, and English phrasal accents. Through a series of probing tasks, we make layer-wise comparisons of English and Ma
Externí odkaz:
http://arxiv.org/abs/2408.13678
Autor:
Doumbouya, Moussa Koulako Bala, Nandi, Ananjan, Poesia, Gabriel, Ghilardi, Davide, Goldie, Anna, Bianchi, Federico, Jurafsky, Dan, Manning, Christopher D.
The safety of Large Language Models (LLMs) remains a critical concern due to a lack of adequate benchmarks for systematically evaluating their ability to resist generating harmful content. Previous efforts towards automated red teaming involve static
Externí odkaz:
http://arxiv.org/abs/2408.04811
Model checklists (Ribeiro et al., 2020) have emerged as a useful tool for understanding the behavior of LLMs, analogous to unit-testing in software engineering. However, despite datasets being a key determinant of model behavior, evaluating datasets,
Externí odkaz:
http://arxiv.org/abs/2408.02919
The ability to communicate uncertainty, risk, and limitation is crucial for the safety of large language models. However, current evaluations of these abilities rely on simple calibration, asking whether the language generated by the model matches ap
Externí odkaz:
http://arxiv.org/abs/2407.07950
Autor:
Shi, Jiatong, Wang, Shih-Heng, Chen, William, Bartelds, Martijn, Kumar, Vanya Bannihatti, Tian, Jinchuan, Chang, Xuankai, Jurafsky, Dan, Livescu, Karen, Lee, Hung-yi, Watanabe, Shinji
ML-SUPERB evaluates self-supervised learning (SSL) models on the tasks of language identification and automatic speech recognition (ASR). This benchmark treats the models as feature extractors and uses a single shallow downstream model, which can be
Externí odkaz:
http://arxiv.org/abs/2406.08641
Autor:
Wu, Zhengxuan, Arora, Aryaman, Wang, Zheng, Geiger, Atticus, Jurafsky, Dan, Manning, Christopher D., Potts, Christopher
Parameter-efficient finetuning (PEFT) methods seek to adapt large neural models via updates to a small number of weights. However, much prior interpretability work has shown that representations encode rich semantic information, suggesting that editi
Externí odkaz:
http://arxiv.org/abs/2404.03592