paper-with-me

Papers

AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation

2024-02-16 · Zhaowei Wang, Wei Fan, Qing Zong, Hongming Zhang, Sehyun Choi, Tianqing Fang, Xin Liu, Yangqiu Song, Ginny Y. Wong, Simon See

Abstraction ability is crucial in human intelligence, which can also benefit various tasks in NLP study. Existing work shows that LLMs are deficient in abstract ability, and how to improve it remains unexplored. In this work, we design the framework AbsInstruct to enhance LLMs' abstraction ability through instruction tuning. The framework builds instructions with in-depth explanations to assist LLMs in capturing the underlying rationale of abstraction. Meanwhile, we introduce a plausibility estimator to select instructions that are more consistent with the abstraction knowledge of LLMs to be aligned. Then, our framework combines abstraction instructions with general-purpose ones to build a hybrid dataset. Extensive experiments and analyses demonstrate that our framework can considerably enhance LLMs' abstraction ability with strong generalization performance while maintaining their general instruction-following abilities.

📄 PDF Abstract BibTeX arXiv:2402.10646

Code (1)

hkust-knowcomp/absinstruct 공식 구현 pytorch

Tasks

Instruction Following

Similar Papers 제목 키워드 기반

Draw Me a Flower: Processing and Grounding Abstraction in Natural Language

2021-06-27 · Royi Lachmy, Valentina Pyatkin, Avshalom Manevich, Reut Tsarfaty

Abstraction is a core tenet of human cognition and communication. When composing natural language instructions, humans naturally evoke abstraction to convey complex procedures in an efficient and concise way. Yet, interp…

4kInstruction FollowingSemantic Parsing

PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning

2024-05-03 · Hyeong Kyu Choi, Yixuan Li

Large Language Models (LLMs) are trained on massive text corpora, which are encoded with diverse personality traits. This triggers an interesting goal of eliciting a desired personality trait from the LLM, and probing it…

Bayesian InferenceIn-Context Learning

Re-Reading Improves Reasoning in Large Language Models

2023-09-12 · Xiaohan Xu, Chongyang Tao, Tao Shen, Can Xu 외

To enhance the reasoning capabilities of off-the-shelf Large Language Models (LLMs), we introduce a simple, yet general and effective prompting method, Re2, i.e., \textbf{Re}-\textbf{Re}ading the question as input. Unlik…

Decoder

Abstraction-of-Thought Makes Language Models Better Reasoners

2024-06-18 · Ruixin Hong, Hongming Zhang, Xiaoman Pan, Dong Yu 외

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 une…

Eliciting Causal Abilities in Large Language Models for Reasoning Tasks

2024-12-19 · Yajing Wang, Zongwei Luo, Jingzhe Wang, Zhanke Zhou 외

Prompt optimization automatically refines prompting expressions, unlocking the full potential of LLMs in downstream tasks. However, current prompt optimization methods are costly to train and lack sufficient interpretabi…

Causal Inference