paper-with-me

홈 › Papers

FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension

2019-08-14 · WS 2019 11 · Yi-Ting Yeh, Yun-Nung Chen

Conversational machine comprehension requires deep understanding of the dialogue flow, and the prior work proposed FlowQA to implicitly model the context representations in reasoning for better understanding. This paper proposes to explicitly model the information gain through dialogue reasoning in order to allow the model to focus on more informative cues. The proposed model achieves state-of-the-art performance in a conversational QA dataset QuAC and sequential instruction understanding dataset SCONE, which shows the effectiveness of the proposed mechanism and demonstrates its capability of generalization to different QA models and tasks.

📄 PDF Abstract BibTeX arXiv:1908.05117

Code (1)

MiuLab/FlowDelta 공식 구현 pytorch

Tasks

Reading Comprehension

Similar Papers 제목 키워드 기반

How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs

2026-06-09 · Zhichen Dong, Yang Li, Yuhan Sun, Weixun Wang 외 arxiv

Token-level credit assignment remains a key obstacle for reinforcement learning (RL) in large language models (LLMs), where RL recipes typically treat all tokens equally, failing to distinguish decisive reasoning steps f…

Reinforcement Learning

Disentangling and Integrating Relational and Sensory Information in Transformer Architectures

2024-05-26 · Awni Altabaa, John Lafferty

Relational reasoning is a central component of generally intelligent systems, enabling robust and data-efficient inductive generalization. Recent empirical evidence shows that many existing neural architectures, includin…

Information RetrievalLanguage ModelingLanguage ModellingRelational Reasoning+1

Modeling Attention Flow on Graphs

2018-11-01 · Xiaoran Xu, Songpeng Zu, Chengliang Gao, Yuan Zhang 외

Real-world scenarios demand reasoning about process, more than final outcome prediction, to discover latent causal chains and better understand complex systems. It requires the learning algorithms to offer both accurate …

Efficient Paths and Dense Rewards: Probabilistic Flow Reasoning for Large Language Models

2026-01-14 · Yan Liu, Feng Zhang, Zhanyu Ma, Jun Xu 외 arxiv

High-quality chain-of-thought has demonstrated strong potential for unlocking the reasoning capabilities of large language models. However, current paradigms typically treat the reasoning process as an indivisible sequen…

Reinforcement Learning

ByteFlow: Language Modeling through Adaptive Byte Compression without a Tokenizer

2026-03-03 · Chunyuan Deng, Sanket Lokegaonkar, Colin Lockard, Besnik Fetahu 외 arxiv

Modern language models still rely on fixed, pre-defined subword tokenizations. Once a tokenizer is trained, the LM can only operate at this fixed level of granularity, which often leads to brittle and counterintuitive be…