7 papers
The First Drop of Ink: Nonlinear Impact of Distracting Information in Long-Context Reasoning
Muhan Gao, Zih-Ching Chen, Kuan-Hao Huang
As large language models are increasingly deployed in retrieval-augmented generation and agentic systems that accumulate extensive context, understanding how distracting informatio…
Learning Multi-Indicator Weights for Data Selection: A Joint Task-Model Adaptation Framework with Efficient Proxies
Jingze Song, Zihao Chen, Wenqing Chen +1
Data selection is a key component of efficient instruction tuning for large language models, as recent work has shown that data quality often matters more than data quantity. Accor…
Visual Preference Optimization with Rubric Rewards
Ya-Qi Yu, Fangyu Hong, Xiangyang Qu +15
The effectiveness of Direct Preference Optimization (DPO) depends on preference data that reflect the quality differences that matter in multimodal tasks. Existing pipelines often…
EVALOOOP: A Self-Consistency-Centered Framework for Assessing Large Language Model Robustness in Programming
Sen Fang, Weiyuan Ding, Mengshi Zhang +2
Evaluating the programming robustness of large language models (LLMs) is paramount for ensuring their reliability in AI-based software development. However, adversarial attacks exh…
VisuRiddles: Fine-grained Perception is a Primary Bottleneck for Multimodal Large Language Models in Abstract Visual Reasoning
Hao Yan, Xingchen Liu, Hao Wang +11
Recent strides in multimodal large language models (MLLMs) have significantly advanced their performance in many reasoning tasks. However, Abstract Visual Reasoning (AVR) remains a…
SLIM: Subtrajectory-Level Elimination for More Effective Reasoning
Xifeng Yao, Chengyuan Ma, Dongyu Lang +8
In recent months, substantial progress has been made in complex reasoning of Large Language Models, particularly through the application of test-time scaling. Notable examples incl…