Zobrazeno 1 - 10
of 48
pro vyhledávání: '"Herzig, Jonathan"'
Large language models (LLMs) are susceptible to hallucinations-outputs that are ungrounded, factually incorrect, or inconsistent with prior generations. We focus on close-book Question Answering (CBQA), where previous work has not fully addressed the
Externí odkaz:
http://arxiv.org/abs/2410.22071
Autor:
Cattan, Arie, Jacovi, Alon, Fabrikant, Alex, Herzig, Jonathan, Aharoni, Roee, Rashkin, Hannah, Marcus, Dror, Hassidim, Avinatan, Matias, Yossi, Szpektor, Idan, Caciularu, Avi
Despite recent advancements in Large Language Models (LLMs), their performance on tasks involving long contexts remains sub-optimal. In-Context Learning (ICL) with few-shot examples may be an appealing solution to enhance LLM performance in this scen
Externí odkaz:
http://arxiv.org/abs/2406.13632
Autor:
Caciularu, Avi, Jacovi, Alon, Ben-David, Eyal, Goldshtein, Sasha, Schuster, Tal, Herzig, Jonathan, Elidan, Gal, Globerson, Amir
Large Language Models (LLMs) often do not perform well on queries that require the aggregation of information across texts. To better evaluate this setting and facilitate modeling efforts, we introduce TACT - Text And Calculations through Tables, a d
Externí odkaz:
http://arxiv.org/abs/2406.03618
Autor:
Gekhman, Zorik, Yona, Gal, Aharoni, Roee, Eyal, Matan, Feder, Amir, Reichart, Roi, Herzig, Jonathan
When large language models are aligned via supervised fine-tuning, they may encounter new factual information that was not acquired through pre-training. It is often conjectured that this can teach the model the behavior of hallucinating factually in
Externí odkaz:
http://arxiv.org/abs/2405.05904
Large language models (LLMs) are prone to hallucinations, which sparked a widespread effort to detect and prevent them. Recent work attempts to mitigate hallucinations by intervening in the model's generation, typically computing representative vecto
Externí odkaz:
http://arxiv.org/abs/2404.09971
Autor:
Singh, Shashwat, Ravfogel, Shauli, Herzig, Jonathan, Aharoni, Roee, Cotterell, Ryan, Kumaraguru, Ponnurangam
Language models often exhibit undesirable behavior, e.g., generating toxic or gender-biased text. In the case of neural language models, an encoding of the undesirable behavior is often present in the model's representations. Thus, one natural (and c
Externí odkaz:
http://arxiv.org/abs/2402.09631
Autor:
Jacovi, Alon, Bitton, Yonatan, Bohnet, Bernd, Herzig, Jonathan, Honovich, Or, Tseng, Michael, Collins, Michael, Aharoni, Roee, Geva, Mor
Prompting language models to provide step-by-step answers (e.g., "Chain-of-Thought") is the prominent approach for complex reasoning tasks, where more accurate reasoning chains typically improve downstream task performance. Recent literature discusse
Externí odkaz:
http://arxiv.org/abs/2402.00559
As instruction-tuned large language models (LLMs) gain global adoption, their ability to follow instructions in multiple languages becomes increasingly crucial. In this work, we investigate how multilinguality during instruction tuning of a multiling
Externí odkaz:
http://arxiv.org/abs/2401.01854
A growing area of research investigates augmenting language models with tools (e.g., search engines, calculators) to overcome their shortcomings (e.g., missing or incorrect knowledge, incorrect logical inferences). Various few-shot tool-usage strateg
Externí odkaz:
http://arxiv.org/abs/2310.10062
Autor:
Muller, Benjamin, Wieting, John, Clark, Jonathan H., Kwiatkowski, Tom, Ruder, Sebastian, Soares, Livio Baldini, Aharoni, Roee, Herzig, Jonathan, Wang, Xinyi
Trustworthy answer content is abundant in many high-resource languages and is instantly accessible through question answering systems, yet this content can be hard to access for those that do not speak these languages. The leap forward in cross-lingu
Externí odkaz:
http://arxiv.org/abs/2305.14332