FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension
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.
Code (1)
Tasks
Reading ComprehensionSimilar Papers 제목 키워드 기반
How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs
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 LearningDisentangling and Integrating Relational and Sensory Information in Transformer Architectures
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+1Modeling Attention Flow on Graphs
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
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 LearningByteFlow: Language Modeling through Adaptive Byte Compression without a Tokenizer
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…