Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Wu, Zeqiu"'
Autor:
Ivison, Hamish, Wang, Yizhong, Liu, Jiacheng, Wu, Zeqiu, Pyatkin, Valentina, Lambert, Nathan, Smith, Noah A., Choi, Yejin, Hajishirzi, Hannaneh
Learning from preference feedback has emerged as an essential step for improving the generation quality and performance of modern language models (LMs). Despite its widespread use, the way preference-based learning is applied varies wildly, with diff
Externí odkaz:
http://arxiv.org/abs/2406.09279
While recent Large Language Models (LLMs) have proven useful in answering user queries, they are prone to hallucination, and their responses often lack credibility due to missing references to reliable sources. An intuitive solution to these issues w
Externí odkaz:
http://arxiv.org/abs/2402.04315
Despite their remarkable capabilities, large language models (LLMs) often produce responses containing factual inaccuracies due to their sole reliance on the parametric knowledge they encapsulate. Retrieval-Augmented Generation (RAG), an ad hoc appro
Externí odkaz:
http://arxiv.org/abs/2310.11511
Autor:
Lu, Bo-Ru, Haduong, Nikita, Lee, Chia-Hsuan, Wu, Zeqiu, Cheng, Hao, Koester, Paul, Utke, Jean, Yu, Tao, Smith, Noah A., Ostendorf, Mari
The capabilities of pretrained language models have opened opportunities to explore new application areas, but applications involving human-human interaction are limited by the fact that most data is protected from public release for privacy reasons.
Externí odkaz:
http://arxiv.org/abs/2307.07047
Autor:
Wu, Zeqiu, Hu, Yushi, Shi, Weijia, Dziri, Nouha, Suhr, Alane, Ammanabrolu, Prithviraj, Smith, Noah A., Ostendorf, Mari, Hajishirzi, Hannaneh
Language models (LMs) often exhibit undesirable text generation behaviors, including generating false, toxic, or irrelevant outputs. Reinforcement learning from human feedback (RLHF) - where human preference judgments on LM outputs are transformed in
Externí odkaz:
http://arxiv.org/abs/2306.01693
Autor:
Wu, Zeqiu, Parish, Ryu, Cheng, Hao, Min, Sewon, Ammanabrolu, Prithviraj, Ostendorf, Mari, Hajishirzi, Hannaneh
In an information-seeking conversation, a user may ask questions that are under-specified or unanswerable. An ideal agent would interact by initiating different response types according to the available knowledge sources. However, most current studie
Externí odkaz:
http://arxiv.org/abs/2207.00746
Autor:
Wu, Zeqiu, Luan, Yi, Rashkin, Hannah, Reitter, David, Hajishirzi, Hannaneh, Ostendorf, Mari, Tomar, Gaurav Singh
Compared to standard retrieval tasks, passage retrieval for conversational question answering (CQA) poses new challenges in understanding the current user question, as each question needs to be interpreted within the dialogue context. Moreover, it ca
Externí odkaz:
http://arxiv.org/abs/2112.08558
Identifying relevant knowledge to be used in conversational systems that are grounded in long documents is critical to effective response generation. We introduce a knowledge identification model that leverages the document structure to provide dialo
Externí odkaz:
http://arxiv.org/abs/2109.04673
The advent of large pre-trained language models has made it possible to make high-quality predictions on how to add or change a sentence in a document. However, the high branching factor inherent to text generation impedes the ability of even the str
Externí odkaz:
http://arxiv.org/abs/2106.07192
Knowledge graphs capture entities and relations from long documents and can facilitate reasoning in many downstream applications. Extracting compact knowledge graphs containing only salient entities and relations is important but challenging for unde
Externí odkaz:
http://arxiv.org/abs/2009.09162