Zobrazeno 1 - 10
of 51
pro vyhledávání: '"Pan, Xiaoman"'
Abstract reasoning, the ability to reason from the abstract essence of a problem, serves as a key to generalization in human reasoning. However, eliciting language models to perform reasoning with abstraction remains unexplored. This paper seeks to b
Externí odkaz:
http://arxiv.org/abs/2406.12442
Autor:
Zhao, Xinran, Zhang, Hongming, Pan, Xiaoman, Yao, Wenlin, Yu, Dong, Wu, Tongshuang, Chen, Jianshu
For a LLM to be trustworthy, its confidence level should be well-calibrated with its actual performance. While it is now common sense that LLM performances are greatly impacted by prompts, the confidence calibration in prompting LLMs has yet to be th
Externí odkaz:
http://arxiv.org/abs/2402.17124
We consider the problem of multi-objective alignment of foundation models with human preferences, which is a critical step towards helpful and harmless AI systems. However, it is generally costly and unstable to fine-tune large foundation models usin
Externí odkaz:
http://arxiv.org/abs/2402.10207
This paper introduces a novel approach to enhance the capabilities of Large Language Models (LLMs) in processing and understanding extensive text sequences, a critical aspect in applications requiring deep comprehension and synthesis of large volumes
Externí odkaz:
http://arxiv.org/abs/2312.08618
Retrieval-augmented language models (RALMs) represent a substantial advancement in the capabilities of large language models, notably in reducing factual hallucination by leveraging external knowledge sources. However, the reliability of the retrieve
Externí odkaz:
http://arxiv.org/abs/2311.09210
Autor:
Wu, Xuansheng, Yao, Wenlin, Chen, Jianshu, Pan, Xiaoman, Wang, Xiaoyang, Liu, Ninghao, Yu, Dong
Large Language Models (LLMs) have achieved remarkable success, where instruction tuning is the critical step in aligning LLMs with user intentions. In this work, we investigate how the instruction tuning adjusts pre-trained models with a focus on int
Externí odkaz:
http://arxiv.org/abs/2310.00492
Large language models (LLMs) have been successfully adapted for interactive decision-making tasks like web navigation. While achieving decent performance, previous methods implicitly assume a forward-only execution mode for the model, where they only
Externí odkaz:
http://arxiv.org/abs/2309.08172
We consider the problem of eliciting compositional generalization capabilities in large language models (LLMs) with a novel type of prompting strategy. Compositional generalization empowers the LLMs to solve problems that are harder than the ones the
Externí odkaz:
http://arxiv.org/abs/2308.00304
Although large-scale pre-trained language models (PTLMs) are shown to encode rich knowledge in their model parameters, the inherent knowledge in PTLMs can be opaque or static, making external knowledge necessary. However, the existing information ret
Externí odkaz:
http://arxiv.org/abs/2307.10442
Autor:
Liang, Zhenwen, Yu, Dian, Pan, Xiaoman, Yao, Wenlin, Zeng, Qingkai, Zhang, Xiangliang, Yu, Dong
Reasoning in mathematical domains remains a significant challenge for relatively small language models (LMs). Many current methods focus on specializing LMs in mathematical reasoning and rely heavily on knowledge distillation from powerful but ineffi
Externí odkaz:
http://arxiv.org/abs/2307.07951