5 papers
ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models
Wenhao Liu, Hao Shi, Yunhe Li +7
Long chain-of-thought (CoT) trajectories in large language model (LLM) reasoning cause severe inference bottlenecks due to rapid key-value (KV) cache growth. Current decoding-time…
Mitigating Prior Errors in Causal Structure Learning: A Resilient Approach via Bayesian Networks
Lyuzhou Chen, Taiyu Ban, Xiangyu Wang +2
Causal structure learning (CSL), a prominent technique for encoding cause-and-effect relationships among variables, through Bayesian Networks (BNs). Although recovering causal stru…
Adaptive Selection of Symbolic Languages for Improving LLM Logical Reasoning
Xiangyu Wang, Haocheng Yang, Fengxiang Cheng +1
Large Language Models (LLMs) still struggle with complex logical reasoning. While previous works achieve remarkable improvements, their performance is highly dependent on the corre…
Integrating Large Language Model for Improved Causal Discovery
Taiyu Ban, Lyuzhou Chen, Derui Lyu +4
Recovering the structure of causal graphical models from observational data is an essential yet challenging task for causal discovery in scientific scenarios. Domain-specific causa…
MTMT: Consolidating Multiple Thinking Modes to Form a Thought Tree for Strengthening LLM
Changcheng Li, Xiangyu Wang, Qiuju Chen +2
Large language models (LLMs) have shown limitations in tasks requiring complex logical reasoning and multi-step problem-solving. To address these challenges, researchers have emplo…