Publications (37)
P^2O: Joint Policy and Prompt Optimization
Xinyu Lu, Kaiqi Zhang, Jinglin Yang +6
Reinforcement Learning with Verifiable Rewards (RLVR) enhances Large Language Model (LLM) reasoning but suffers from advantage collapse on ``hard samples'' where all rollouts fail.…
Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards
Zhengzhao Ma, Xueru Wen, Boxi Cao +6
Reinforcement Learning from Verifiable Rewards (RLVR) significantly enhances large language models (LLMs) reasoning but severely suffers from calibration degeneration, where models…
Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models
Jiasheng Zheng, Boxi Cao, Zhengzhao Ma +5
In recent years, researchers have proposed numerous benchmarks to evaluate the impressive coding capabilities of large language models (LLMs). However, current benchmarks primarily…
Towards Universal Dense Blocking for Entity Resolution
Tianshu Wang, Hongyu Lin, Xianpei Han +3
Blocking is a critical step in entity resolution, and the emergence of neural network-based representation models has led to the development of dense blocking as a promising approa…
PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction
Zhuoqun Li, Boxi Cao, Jiawei Chen +11
Long-horizon behavior prediction aims to infer a user's next action based on a lengthy historical sequence, playing a crucial role in artificial intelligence field. The rise of lar…
DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations
Jiazhen Jiang, Boxi Cao, Lingyong Yan +6
As autonomous agents rapidly evolve, their ability to reliably manipulate ubiquitous digital documents has become critical for enabling general-purpose AI assistants and automating…
CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark
Yuan Yao, Qingxiu Dong, Jian Guan +32
Realizing general-purpose language intelligence has been a longstanding goal for natural language processing, where standard evaluation benchmarks play a fundamental and guiding ro…
OmniFocus: Query-Guided Modality-Balanced Token Compression for Omni-Modal Large Language Models
Shijie Cao, Qingyu Zhang, Boxi Yu +6
Omni modal large language models (OmniLLMs) have attracted wide attention for their ability to jointly process audio and video, but they generate large token sequences under audio-…
Multi-Facet Counterfactual Learning for Content Quality Evaluation
Jiasheng Zheng, Hongyu Lin, Boxi Cao +4
Evaluating the quality of documents is essential for filtering valuable content from the current massive amount of information. Conventional approaches typically rely on a single s…
Towards Scalable Automated Alignment of LLMs: A Survey
Boxi Cao, Keming Lu, Xinyu Lu +10
Alignment is the most critical step in building large language models (LLMs) that meet human needs. With the rapid development of LLMs gradually surpassing human capabilities, trad…
Memorizing is Not Enough: Deep Knowledge Injection Through Reasoning
Ruoxi Xu, Yunjie Ji, Boxi Cao +7
Although large language models (LLMs) excel in knowledge recall and reasoning, their static nature leads to outdated information as the real world evolves or when adapting to domai…
ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases
Qiaoyu Tang, Ziliang Deng, Hongyu Lin +4
Enabling large language models to utilize real-world tools effectively is crucial for achieving embodied intelligence. Existing approaches to tool learning have either primarily re…
Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Models
Boxi Cao, Qiaoyu Tang, Hongyu Lin +6
Memory is one of the most essential cognitive functions serving as a repository of world knowledge and episodes of activities. In recent years, large-scale pre-trained language mod…
Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering
Xinyan Guan, Yanjiang Liu, Xinyu Lu +8
The evolution of machine learning has increasingly prioritized the development of powerful models and more scalable supervision signals. However, the emergence of foundation models…
StructEval: Deepen and Broaden Large Language Model Assessment via Structured Evaluation
Boxi Cao, Mengjie Ren, Hongyu Lin +4
Evaluation is the baton for the development of large language models. Current evaluations typically employ a single-item assessment paradigm for each atomic test objective, which s…
ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models
Jun Zhang, Jiasheng Zheng, Boxi Cao +5
The emergence of Large Reasoning Models has introduced exceptionally long Chain-of-Thought traces, creating a transparency burden where critical logic is often buried under massive…
Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination
Jiasheng Zheng, Boxi Cao, Boxi Yu +6
Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as the cornerstone for shaping the remarkable coding abilities of Large Language Models (LLMs). However,…
The Life Cycle of Knowledge in Big Language Models: A Survey
Boxi Cao, Hongyu Lin, Xianpei Han +1
Knowledge plays a critical role in artificial intelligence. Recently, the extensive success of pre-trained language models (PLMs) has raised significant attention about how knowled…
Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards
Mengjie Ren, Jie Lou, Boxi Cao +6
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective paradigm for improving the reasoning capabilities of large language models. However, RLVR training…
Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal View
Boxi Cao, Hongyu Lin, Xianpei Han +2
Prompt-based probing has been widely used in evaluating the abilities of pretrained language models (PLMs). Unfortunately, recent studies have discovered such an evaluation may be…
The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?
Xinyu Lu, Tianshu Wang, Pengbo Wang +8
Current AI benchmarks evaluate agents on task execution within human-designed workflows. These evaluations fundamentally fail to measure a critical next-level capability: whether m…
ScaleBox: Enabling High-Fidelity and Scalable Code Verification for Large Language Models
Jiasheng Zheng, Xin Zheng, Boxi Cao +8
Code sandboxes have emerged as a critical infrastructure for advancing the coding capabilities of large language models, providing verifiable feedback for both RL training and eval…
URL: Universal Referential Knowledge Linking via Task-instructed Representation Compression
Zhuoqun Li, Hongyu Lin, Tianshu Wang +7
Linking a claim to grounded references is a critical ability to fulfill human demands for authentic and reliable information. Current studies are limited to specific tasks like inf…
A Roadmap for Big Model
Sha Yuan, Hanyu Zhao, Shuai Zhao +97
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm. Researchers have achieved various outcomes in the c…
Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation
Ruotong Pan, Boxi Cao, Hongyu Lin +5
The rapid development of large language models has led to the widespread adoption of Retrieval-Augmented Generation (RAG), which integrates external knowledge to alleviate knowledg…
When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models
Yingzhi Mao, Chunkang Zhang, Junxiang Wang +6
Large Reasoning Models (LRMs) achieve strong performance on complex multi-step reasoning, yet they still exhibit severe safety failures such as harmful content generation. Existing…
Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models
Xinru Yan, Boxi Cao, Yaojie Lu +4
Native Omni-modal Large Language Models (OLLMs) have shifted from pipeline architectures to unified representation spaces. However, this native integration gives rise to a critical…
All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG
Dan Wang, Guozhao Mo, Yafei Shi +9
Multilingual Retrieval-Augmented Generation (mRAG) leverages cross-lingual evidence to ground Large Language Models (LLMs) in global knowledge. However, we show that current mRAG s…
Learning or Self-aligning? Rethinking Instruction Fine-tuning
Mengjie Ren, Boxi Cao, Hongyu Lin +6
Instruction Fine-tuning~(IFT) is a critical phase in building large language models~(LLMs). Previous works mainly focus on the IFT's role in the transfer of behavioral norms and th…
Spiral of Silence: How is Large Language Model Killing Information Retrieval? -- A Case Study on Open Domain Question Answering
Xiaoyang Chen, Ben He, Hongyu Lin +5
The practice of Retrieval-Augmented Generation (RAG), which integrates Large Language Models (LLMs) with retrieval systems, has become increasingly prevalent. However, the repercus…
Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces
Jiawei Chen, Ruoxi Xu, Boxi Cao +11
The emergence of Large Language Models (LLMs) has illuminated the potential for a general-purpose user simulator. However, existing benchmarks remain constrained to isolated scenar…
Critic-CoT: Boosting the reasoning abilities of large language model via Chain-of-thoughts Critic
Xin Zheng, Jie Lou, Boxi Cao +7
Self-critic has become a crucial mechanism for enhancing the reasoning performance of LLMs. However, current approaches mainly involve basic prompts for intuitive instance-level fe…
LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents
Xiaoxuan Peng, Kaiqi Zhang, Xinyu Lu +5
Mastering terminal environments requires language agents capable of multi-step planning, feedback-grounded execution, and dynamic state adaptation. However, training such agents is…
Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases
Boxi Cao, Hongyu Lin, Xianpei Han +5
Previous literatures show that pre-trained masked language models (MLMs) such as BERT can achieve competitive factual knowledge extraction performance on some datasets, indicating…
Pre-training to Match for Unified Low-shot Relation Extraction
Fangchao Liu, Hongyu Lin, Xianpei Han +2
Low-shot relation extraction~(RE) aims to recognize novel relations with very few or even no samples, which is critical in real scenario application. Few-shot and zero-shot RE are…
Learning In-context Learning for Named Entity Recognition
Jiawei Chen, Yaojie Lu, Hongyu Lin +7
Named entity recognition in real-world applications suffers from the diversity of entity types, the emergence of new entity types, and the lack of high-quality annotations. To addr…
MetaphorVU: Towards Metaphorical Video Understanding
Zhuoqun Li, Boxi Cao, Guiping Jiang +13
Metaphorical videos are prevalent across various real-world scenarios to convey complex ideas, and understanding them typically requires high-order cognitive capabilities. The lack…