31 papers
How to Use Parallel Data for Multilingual Pretraining
Zhihong Huang, Yao Lu, Derek F. Wong +2
High-quality human-translated parallel corpora can improve cross-lingual transfer, but are typically too small for large-scale pretraining. Machine-translated web corpora help over…
SrDetection: A Self-Referential Framework for Data Leakage Detection in Code Large Language Models
Shuaimin Li, Liyang Fan, Zeyang Li +9
Evaluating code large language models (Code LLMs) requires reliable detection of data leakage, where benchmark performance is artificially inflated by exposure to benchmark data du…
PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination
Qiyao Wang, Xinyi Chen, Longze Chen +4
Patent examination is a complex, multi-stage process requiring both technical expertise and legal reasoning, increasingly challenged by rising application volumes. Prior benchmarks…
InteractWeb-Bench: Can Multimodal Agent Escape Blind Execution in Interactive Website Generation?
Qiyao Wang, Haoran Hu, Longze Chen +4
With the advancement of multimodal large language models (MLLMs) and coding agents, the website development has shifted from manual programming to agent-based project-level code sy…
PLOT: Enhancing Preference Learning via Optimal Transport
Liang Zhu, Yuelin Bai, Xiankun Ren +6
Preference learning in Large Language Models (LLMs) has advanced significantly, yet existing methods remain limited by modest performance gains, high computational costs, hyperpara…
FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration
Qiyao Wang, Hongbo Wang, Longze Chen +6
Scientific idea generation (SIG) is critical to AI-driven autonomous research, yet existing approaches are often constrained by a static retrieval-then-generation paradigm, leading…
CoTJudger: A Graph-Driven Framework for Automatic Evaluation of Chain-of-Thought Efficiency and Redundancy in LRMs
Siyi Li, Jiajun Shi, Shiwen Ni +9
Large Reasoning Models (LRMs) have demonstrated strong performance by producing extended Chain-of-Thought (CoT) traces before answering. However, this paradigm often induces over-r…
RuCL: Stratified Rubric-Based Curriculum Learning for Multimodal Large Language Model Reasoning
Yukun Chen, Jiaming Li, Longze Chen +10
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a prevailing paradigm for enhancing reasoning in Multimodal Large Language Models (MLLMs). However, relying sol…
SC-Arena: A Natural Language Benchmark for Single-Cell Reasoning with Knowledge-Augmented Evaluation
Jiahao Zhao, Feng Jiang, Shaowei Qin +5
Large language models (LLMs) are increasingly applied in scientific research, offering new capabilities for knowledge discovery and reasoning. In single-cell biology, however, eval…
Beyond Quantity: Trajectory Diversity Scaling for Code Agents
Guhong Chen, Chenghao Sun, Cheng Fu +16
As code large language models (LLMs) evolve into tool-interactive agents via the Model Context Protocol (MCP), their generalization is increasingly limited by low-quality synthetic…
RxSafeBench: Identifying Medication Safety Issues of Large Language Models in Simulated Consultation
Jiahao Zhao, Luxin Xu, Minghuan Tan +4
Numerous medical systems powered by Large Language Models (LLMs) have achieved remarkable progress in diverse healthcare tasks. However, research on their medication safety remains…
Automatic Paper Reviewing with Heterogeneous Graph Reasoning over LLM-Simulated Reviewer-Author Debates
Shuaimin Li, Liyang Fan, Yufang Lin +5
Existing paper review methods often rely on superficial manuscript features or directly on large language models (LLMs), which are prone to hallucinations, biased scoring, and limi…
ToolRM: Towards Agentic Tool-Use Reward Modeling
Renhao Li, Jianhong Tu, Yang Su +6
Reward models (RMs) play a critical role in aligning large language models (LLMs) with human preferences. Yet in the domain of tool learning, the lack of RMs specifically designed…
Structuring Reasoning for Complex Rules Beyond Flat Representations
Zhihao Yang, Ancheng Xu, Jingpeng Li +11
Large language models (LLMs) face significant challenges when processing complex rule systems, as they typically treat interdependent rules as unstructured textual data rather than…
STORYTELLER: An Enhanced Plot-Planning Framework for Coherent and Cohesive Story Generation
Jiaming Li, Yukun Chen, Ziqiang Liu +10
Stories are central to human culture, serving to share ideas, preserve traditions, and foster connections. Automatic story generation, a key advancement in artificial intelligence…
Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models
Jiaming Li, Haoran Ye, Yukun Chen +5
Sparse Autoencoders (SAEs) are a cornerstone of mechanistic interpretability. Existing training methods inherit the Block Training paradigm from LLM pre-training, which introduces…
Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolation
Dingwei Chen, Ziqiang Liu, Feiteng Fang +6
Large Language Models (LLMs) demonstrate remarkable capabilities in text understanding and generation. However, their tendency to produce factually inconsistent outputs, commonly r…
CLaSp: In-Context Layer Skip for Self-Speculative Decoding
Longze Chen, Renke Shan, Huiming Wang +6
Speculative decoding (SD) is a promising method for accelerating the decoding process of Large Language Models (LLMs). The efficiency of SD primarily hinges on the consistency betw…
Interpretable graph-based models on multimodal biomedical data integration: A technical review and benchmarking
Alireza Sadeghi, Farshid Hajati, Ahmadreza Argha +3
Integrating heterogeneous biomedical data including imaging, omics, and clinical records supports accurate diagnosis and personalised care. Graph-based models fuse such non-Euclide…
Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity
Feiteng Fang, Dingwei Chen, Xiang Huang +10
Currently, most reinforcement learning tasks focus on domains like mathematics and programming, where verification is relatively straightforward. However, in subjective tasks such…
EVADE-Bench: Multimodal Benchmark for Evaluating and Enhancing Evasive Content Detection
Ancheng Xu, Zhihao Yang, Jingpeng Li +9
E-commerce platforms increasingly rely on Large Language Models (LLMs) and Vision Language Models (VLMs) to detect illicit or misleading product content. However, these models rema…
IPBench: Benchmarking the Knowledge of Large Language Models in Intellectual Property
Qiyao Wang, Guhong Chen, Hongbo Wang +20
Intellectual Property (IP) is a highly specialized domain that integrates technical and legal knowledge, making it inherently complex and knowledge-intensive. Recent advancements i…
Quantification of Large Language Model Distillation
Sunbowen Lee, Junting Zhou, Chang Ao +11
Model distillation is a fundamental technique in building large language models (LLMs), transferring knowledge from a teacher model to a student model. However, distillation can le…
xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking
Sunbowen Lee, Shiwen Ni, Chi Wei +7
Safety alignment mechanism are essential for preventing large language models (LLMs) from generating harmful information or unethical content. However, cleverly crafted prompts can…