9 papers
CoCoGEC: Counterfactual Generation for Robust Grammatical Error Correction
Qianyu Wang, Xiaoman Wang, Yuanyuan Liang +2
Grammatical error correction (GEC) systems are usually trained and evaluated on GEC benchmarks, but their performance often drops sharply once the surrounding context is slightly p…
LiveBrowseComp: Are Search Agents Searching, or Just Verifying What They Already Know?
HuiMing Fan, Xiao Wang, Zheng Chu +5
Are LLM-based search agents genuinely searching, or using the web to verify what they already know? We study this question on BrowseComp with three diagnostics. Our analysis reveal…
Precedent-Informed Reasoning: Mitigating Overthinking in Large Reasoning Models via Test-Time Precedent Learning
Qianyue Wang, Jinwu Hu, Huanxiang Lin +5
Reasoning in Large Language Models (LLMs) often suffers from inefficient long chain-of-thought traces with redundant self-exploration and validation, which inflate computational co…
Beyond Model Scaling: Test-Time Intervention for Efficient Deep Reasoning
Qianyue Wang, Jinwu Hu, Yufeng Wang +5
Large Reasoning Models (LRMs) excel at multi-step reasoning but often suffer from inefficient reasoning processes like overthinking and overshoot, where excessive or misdirected re…
EvidFuse: Writing-Time Evidence Learning for Consistent Text-Chart Data Reporting
Huanxiang Lin, Qianyue Wang, Jinwu Hu +3
Data-driven reports communicate decision-relevant insights by tightly interleaving narrative text with charts grounded in underlying tables. However, current LLM-based systems typi…
Curse of High Dimensionality Issue in Transformer for Long-context Modeling
Shuhai Zhang, Zeng You, Yaofo Chen +5
Transformer-based large language models (LLMs) excel in natural language processing tasks by capturing long-range dependencies through self-attention mechanisms. However, long-cont…