5 papers
DALM: A Domain-Algebraic Language Model via Three-Phase Structured Generation
Chao Li
Large language models compress heterogeneous knowledge into a single parameter space, allowing facts from different domains to interfere during generation. We propose DALM, a Domai…
Reasoning as Data: Representation-Computation Unity and Its Implementation in a Domain-Algebraic Inference Engine
Chao Li, Yuru Wang
Every existing knowledge system separates storage from computation. We show this separation is unnecessary and eliminate it. In a standard triple is_a(Apple, Company), domain conte…
Think Less, Know More: State-Aware Reasoning Compression with Knowledge Guidance for Efficient Reasoning
Yi Sui, Chaozhuo Li, Dawei Song
Large Reasoning Models (LRMs) achieve strong performance on complex tasks by leveraging long Chain-of-Thought (CoT), but often suffer from overthinking, leading to excessive reason…
Clarifying Before Reasoning: A Coq Prover with Structural Context
Yanzhen Lu, Hanbin Yang, Xiaodie Wang +6
In this work, we investigate whether improving task clarity can enhance reasoning ability of large language models, focusing on theorem proving in Coq. We introduce a concept-level…
Hierarchical Attention Generates Better Proofs
Jianlong Chen, Chao Li, Yang Yuan +1
Large language models (LLMs) have shown promise in formal theorem proving, but their token-level processing often fails to capture the inherent hierarchical nature of mathematical…