Publications (140)
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.…
Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch
Xueru Wen, Jie Lou, Zichao Li +9
Reward models (RMs) are crucial for aligning large language models (LLMs) with human preferences. However, most RM research is centered on English and relies heavily on synthetic r…
RefCritic: Training Long Chain-of-Thought Critic Models with Refinement Feedback
Qiaoyu Tang, Hao Xiang, Le Yu +6
With the rapid advancement of Large Language Models (LLMs), developing effective critic modules for precise guidance has become crucial yet challenging. In this paper, we initially…
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…
LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?
Guozhao Mo, Wenliang Zhong, Jiawei Chen +7
Model Context Protocol (MCP) has become a key infrastructure for connecting LLMs with external tools, scaling to 10,000+ MCP servers with diverse tools. Unfortunately, there is sti…
Behavioral Embeddings of Programs: A Quasi-Dynamic Approach for Optimization Prediction
Haolin Pan, Jinyuan Dong, Hongbin Zhang +3
Learning effective numerical representations, or embeddings, of programs is a fundamental prerequisite for applying machine learning to automate and enhance compiler optimization.…
De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention
Wenkai Zhang, Hongyu Lin, Xianpei Han +1
Distant supervision tackles the data bottleneck in NER by automatically generating training instances via dictionary matching. Unfortunately, the learning of DS-NER is severely dic…
Open Grounded Planning: Challenges and Benchmark Construction
Shiguang Guo, Ziliang Deng, Hongyu Lin +3
The emergence of large language models (LLMs) has increasingly drawn attention to the use of LLMs for human-like planning. Existing work on LLM-based planning either focuses on lev…
RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing
Hao Xiang, Tianyi Tang, Yang Su +10
Recent advancements in Large Language Models (LLMs) have shown outstanding potential for role-playing applications. Evaluating these capabilities is becoming crucial yet remains ch…
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…
ConsistentChat: Building Skeleton-Guided Consistent Multi-Turn Dialogues for Large Language Models from Scratch
Jiawei Chen, Xinyan Guan, Qianhao Yuan +7
Current instruction data synthesis methods primarily focus on single-turn instructions and often neglect cross-turn coherence, resulting in context drift and reduced task completio…
ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers
Qianhao Yuan, Qingyu Zhang, Yanjiang Liu +6
Multimodal Large Language Models (MLLMs) suffer from high computational costs due to their massive size and the large number of visual tokens. In this paper, we investigate layer-w…
TuneAgent: Agentic Operating System Kernel Tuning with Reinforcement Learning
Hongyu Lin, Yuchen Li, Haoran Luo +4
Linux kernel tuning is essential for optimizing operating system (OS) performance, yet remains challenging due to the complex kernel space, sparse performance feedback, and strong…
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…
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…
DLUE: Benchmarking Document Language Understanding
Ruoxi Xu, Hongyu Lin, Xinyan Guan +3
Understanding documents is central to many real-world tasks but remains a challenging topic. Unfortunately, there is no well-established consensus on how to comprehensively evaluat…
SAISA: Towards Multimodal Large Language Models with Both Training and Inference Efficiency
Qianhao Yuan, Yanjiang Liu, Yaojie Lu +4
Multimodal Large Language Models (MLLMs) mainly fall into two architectures, each involving a trade-off between training and inference efficiency: embedding space alignment (e.g.,…
DeepRAG: Thinking to Retrieve Step by Step for Large Language Models
Xinyan Guan, Jiali Zeng, Fandong Meng +6
Large Language Models (LLMs) have shown remarkable reasoning capabilities, while their practical applications are limited by severe factual hallucinations due to limitations in the…
Procedural Text Understanding via Scene-Wise Evolution
Jialong Tang, Hongyu Lin, Meng Liao +5
Procedural text understanding requires machines to reason about entity states within the dynamical narratives. Current procedural text understanding approaches are commonly \textbf…
Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction
Tianyun Zhong, Guozhao Mo, Yanjiang Liu +9
With the emergence of large language models (LLMs), there is an expectation that LLMs can effectively extract explicit information from complex real-world documents (e.g., papers,…
Self-Retrieval: End-to-End Information Retrieval with One Large Language Model
Qiaoyu Tang, Jiawei Chen, Zhuoqun Li +10
The rise of large language models (LLMs) has significantly transformed both the construction and application of information retrieval (IR) systems. However, current interactions be…
Kerr-nonlinearity Enhanced Conventional Photon Blockade in Second-order-nonlinear System
Hongyu Lin, Xiaoqian Wang, Zhihai Yao +1
In the recent publication [Phys. Rev. B 87, 235319 (2013)], the conventional photon blockade(CPB) was studied for the low frequency mode in a second-order nonlinear system. In this…
On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation
Xueru Wen, Jie Lou, Xinyu Lu +8
Hallucination occurs when large language models exhibit behavior that deviates from the boundaries of their knowledge during response generation. To address this critical issue, pr…
Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning
Xinyan Guan, Jiali Zeng, Chunlei Xin +5
Large language models generate computationally expensive yet semantically void reasoning on beyond-capability tasks, creating risks where plausible-sounding but incorrect derivatio…
Syntactic and Semantic-driven Learning for Open Information Extraction
Jialong Tang, Yaojie Lu, Hongyu Lin +4
One of the biggest bottlenecks in building accurate, high coverage neural open IE systems is the need for large labelled corpora. The diversity of open domain corpora and the varie…
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…
StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
Zhuoqun Li, Xuanang Chen, Haiyang Yu +7
Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) in many knowledge-based tasks. However, existing RAG methods struggle with k…
Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Window
Qiaoyu Tang, Hao Xiang, Le Yu +11
While recent advances in reasoning models have demonstrated cognitive behaviors through reinforcement learning, existing approaches struggle to invoke deep reasoning capabilities i…
ISCAS at SemEval-2020 Task 5: Pre-trained Transformers for Counterfactual Statement Modeling
Yaojie Lu, Annan Li, Hongyu Lin +2
ISCAS participated in two subtasks of SemEval 2020 Task 5: detecting counterfactual statements and detecting antecedent and consequence. This paper describes our system which is ba…
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…
Harvesting Event Schemas from Large Language Models
Jialong Tang, Hongyu Lin, Zhuoqun Li +3
Event schema provides a conceptual, structural and formal language to represent events and model the world event knowledge. Unfortunately, it is challenging to automatically induce…
ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation
Qingyu Zhang, Qianhao Yuan, Hongyu Lin +7
The paper proposes ShortOPD, a short-to-long on-policy distillation method that recovers the generation quality of structured-pruned large language models by focusing training on e…
Imandra CodeLogician: Neuro-Symbolic Reasoning for Precise Analysis of Software Logic
Hongyu Lin, Samer Abdallah, Makar Valentinov +5
Large Language Models (LLMs) have shown strong performance on code understanding tasks, yet they fundamentally lack the ability to perform precise, exhaustive mathematical reasonin…
PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing
Zhuoqun Li, Xuanang Chen, Hongyu Lin +5
As researchers delve more deeply into their work, paper search requirements may become more flexible, sometimes involving specific details such as module configuration rather than…
CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution
Ruiyang Xu, Jialun Cao, Yaojie Lu +6
Code benchmarks such as HumanEval are widely adopted to evaluate Large Language Models' (LLMs) coding capabilities. However, there is an unignorable programming language bias in ex…
Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofitting
Xinyan Guan, Yanjiang Liu, Hongyu Lin +4
Incorporating factual knowledge in knowledge graph is regarded as a promising approach for mitigating the hallucination of large language models (LLMs). Existing methods usually on…
Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery
Tianyun Zhong, Wangyi Jiang, Wei Wang +15
Large language models (LLMs) excel at answering pre-specified questions, yet their ability to navigate the open-ended, pre-conclusion stage of discovery remains largely unmeasured.…
Influence of External Information on Large Language Models Mirrors Social Cognitive Patterns
Ning Bian, Hongyu Lin, Peilin Liu +5
Social cognitive theory explains how people learn and acquire knowledge through observing others. Recent years have witnessed the rapid development of large language models (LLMs),…
SCA: Segment-Wise CoT Compression with Answer Alignment
Ye Tian, Hongyu Lin, Aijun Liu
Chain-of-thought (CoT) reasoning improves problem solving, but long think traces increase inference cost. Existing CoT compression methods usually optimize completion-level length.…
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…
Cost-sensitive Regularization for Label Confusion-aware Event Detection
Hongyu Lin, Yaojie Lu, Xianpei Han +1
In supervised event detection, most of the mislabeling occurs between a small number of confusing type pairs, including trigger-NIL pairs and sibling sub-types of the same coarse t…
REInstruct: Building Instruction Data from Unlabeled Corpus
Shu Chen, Xinyan Guan, Yaojie Lu +3
Manually annotating instruction data for large language models is difficult, costly, and hard to scale. Meanwhile, current automatic annotation methods typically rely on distilling…
ShortGPT: Layers in Large Language Models are More Redundant Than You Expect
Xin Men, Mingyu Xu, Qingyu Zhang +5
As Large Language Models (LLMs) continue to advance in performance, their size has escalated significantly, with current LLMs containing billions or even trillions of parameters. H…
Few-shot Named Entity Recognition with Self-describing Networks
Jiawei Chen, Qing Liu, Hongyu Lin +2
Few-shot NER needs to effectively capture information from limited instances and transfer useful knowledge from external resources. In this paper, we propose a self-describing mech…
Adaptive Scaling for Sparse Detection in Information Extraction
Hongyu Lin, Yaojie Lu, Xianpei Han +1
This paper focuses on detection tasks in information extraction, where positive instances are sparsely distributed and models are usually evaluated using F-measure on positive clas…
Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks
Hongyu Lin, Yaojie Lu, Xianpei Han +1
Sequential labeling-based NER approaches restrict each word belonging to at most one entity mention, which will face a serious problem when recognizing nested entity mentions. In t…
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…
StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agents
Haojie Hao, Longkun Hao, Yihang Lou +8
Reinforcement Learning (RL) has become a promising approach for improving GUI Agents in long-horizon, stochastic digital environments, but trajectory-level success feedback is too…
Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching
Tianshu Wang, Xiaoyang Chen, Hongyu Lin +5
Entity matching (EM) is a critical step in entity resolution (ER). Recently, entity matching based on large language models (LLMs) has shown great promise. However, current LLM-bas…
Compositional Sparsity as an Inductive Bias for Neural Architecture Design
Hongyu Lin, Antonio Briola, Yuanrong Wang +1
Identifying the structural priors that enable Deep Neural Networks (DNNs) to overcome the curse of dimensionality is a fundamental challenge in machine learning theory. Existing li…
Bridging the Gap between Language Model and Reading Comprehension: Unsupervised MRC via Self-Supervision
Ning Bian, Xianpei Han, Bo Chen +3
Despite recent success in machine reading comprehension (MRC), learning high-quality MRC models still requires large-scale labeled training data, even using strong pre-trained lang…
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…
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…
KGCompiler: Deep Learning Compilation Optimization for Knowledge Graph Complex Logical Query Answering
Hongyu Lin, Haoran Luo, Hanghang Cao +6
Complex Logical Query Answering (CLQA) involves intricate multi-hop logical reasoning over large-scale and potentially incomplete Knowledge Graphs (KGs). Although existing CLQA alg…
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…
AI-Salesman: Towards Reliable Large Language Model Driven Telemarketing
Qingyu Zhang, Chunlei Xin, Xuanang Chen +7
Goal-driven persuasive dialogue, exemplified by applications like telemarketing, requires sophisticated multi-turn planning and strict factual faithfulness, which remains a signifi…
DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking
Zhuoqun Li, Haiyang Yu, Xuanang Chen +6
Designing solutions for complex engineering challenges is crucial in human production activities. However, previous research in the retrieval-augmented generation (RAG) field has n…
DBCopilot: Natural Language Querying over Massive Databases via Schema Routing
Tianshu Wang, Xiaoyang Chen, Hongyu Lin +4
The development of Natural Language Interfaces to Databases (NLIDBs) has been greatly advanced by the advent of large language models (LLMs), which provide an intuitive way to tran…
DOMAINEVAL: An Auto-Constructed Benchmark for Multi-Domain Code Generation
Qiming Zhu, Jialun Cao, Yaojie Lu +4
Code benchmarks such as HumanEval are widely adopted to evaluate the capabilities of Large Language Models (LLMs), providing insights into their strengths and weaknesses. However,…
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…
Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning
Haolin Pan, Hongyu Lin, Haoran Luo +5
Compiler auto-tuning optimizes pass sequences to improve performance metrics such as Intermediate Representation (IR) instruction count. Although recent advances leveraging Large L…
MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models
Zhichao Yang, Yuanze Hu, Haojie Hao +7
Mobile agents are increasingly expected to operate everyday applications from screenshots and language goals, where reliable control requires reasoning over screen affordances, mul…
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…
Element Intervention for Open Relation Extraction
Fangchao Liu, Lingyong Yan, Hongyu Lin +2
Open relation extraction aims to cluster relation instances referring to the same underlying relation, which is a critical step for general relation extraction. Current OpenRE mode…
A Rigorous Study on Named Entity Recognition: Can Fine-tuning Pretrained Model Lead to the Promised Land?
Hongyu Lin, Yaojie Lu, Jialong Tang +4
Fine-tuning pretrained model has achieved promising performance on standard NER benchmarks. Generally, these benchmarks are blessed with strong name regularity, high mention covera…
Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models
Hao Xiang, Bowen Yu, Hongyu Lin +7
The key to effective alignment lies in high-quality preference data. Recent research has focused on automated alignment, which involves developing alignment systems with minimal hu…
AI for social science and social science of AI: A Survey
Ruoxi Xu, Yingfei Sun, Mengjie Ren +5
Recent advancements in artificial intelligence, particularly with the emergence of large language models (LLMs), have sparked a rethinking of artificial general intelligence possib…
Few-shot Named Entity Recognition via Superposition Concept Discrimination
Jiawei Chen, Hongyu Lin, Xianpei Han +4
Few-shot NER aims to identify entities of target types with only limited number of illustrative instances. Unfortunately, few-shot NER is severely challenged by the intrinsic preci…
Expanding the Boundaries of Vision Prior Knowledge in Multi-modal Large Language Models
Qiao Liang, Yanjiang Liu, Weixiang Zhou +7
Does the prior knowledge of the vision encoder constrain the capability boundary of Multi-modal Large Language Models (MLLMs)? While most existing research treats MLLMs as unified…
Granger Causality Detection with Kolmogorov-Arnold Networks
Hongyu Lin, Mohan Ren, Paolo Barucca +1
Discovering causal relationships in time series data is central in many scientific areas, ranging from economics to climate science. Granger causality is a powerful tool for causal…
AwareCompiler: Agentic Context-Aware Compiler Optimization via a Synergistic Knowledge-Data Driven Framework
Hongyu Lin, Haolin Pan, Haoran Luo +5
Compiler optimization is crucial for enhancing program performance by transforming the sequence of optimization passes while maintaining correctness. Despite the promising potentia…
Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?
Xueru Wen, Jie Lou, Yaojie Lu +7
Reward Models (RMs) are crucial for aligning language models with human preferences. Currently, the evaluation of RMs depends on measuring accuracy against a validation set of manu…
Across Programming Language Silos: A Study on Cross-Lingual Retrieval-augmented Code Generation
Qiming Zhu, Jialun Cao, Xuanang Chen +6
Current research on large language models (LLMs) with retrieval-augmented code generation (RACG) has largely focused on single-language settings, leaving their cross-lingual effect…
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…
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…
Meta-Cognitive Analysis: Evaluating Declarative and Procedural Knowledge in Datasets and Large Language Models
Zhuoqun Li, Hongyu Lin, Yaojie Lu +3
Declarative knowledge and procedural knowledge are two key parts in meta-cognitive theory, and these two hold significant importance in pre-training and inference of LLMs. However,…
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…
End-to-End Neural Event Coreference Resolution
Yaojie Lu, Hongyu Lin, Jialong Tang +2
Traditional event coreference systems usually rely on pipeline framework and hand-crafted features, which often face error propagation problem and have poor generalization ability.…
Base of RoPE Bounds Context Length
Xin Men, Mingyu Xu, Bingning Wang +4
Position embedding is a core component of current Large Language Models (LLMs). Rotary position embedding (RoPE), a technique that encodes the position information with a rotation…
ECO v1: Towards Event-Centric Opinion Mining
Ruoxi Xu, Hongyu Lin, Meng Liao +5
Events are considered as the fundamental building blocks of the world. Mining event-centric opinions can benefit decision making, people communication, and social good. Unfortunate…
Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learning
Zichao Li, Jie Lou, Fangchen Dong +8
Reinforcement learning significantly enhances LLM capabilities but suffers from a critical issue: length inflation, where models adopt verbosity or inefficient reasoning to maximiz…
Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models?
Ning Bian, Xianpei Han, Hongyu Lin +3
Building machines with commonsense has been a longstanding challenge in NLP due to the reporting bias of commonsense rules and the exposure bias of rule-based commonsense reasoning…
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…
Correcting What You Cannot See: Credit Assignment for Perception Distillation in Multimodal Reasoners
Feng Xiong, Leyan Xue, Hongyu Lin
The paper proposes Perception-Correction Distillation (PCD), a label‑free method that uses downstream failures and teacher‑student disagreement to pinpoint and correct perception e…
Universal Information Extraction as Unified Semantic Matching
Jie Lou, Yaojie Lu, Dai Dai +5
The challenge of information extraction (IE) lies in the diversity of label schemas and the heterogeneity of structures. Traditional methods require task-specific model design and…
Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization
Hao Xiang, Qiaoyu Tang, Le Yu +8
Reinforcement Learning (RL) with verifiable environments has emerged as a powerful approach for enhancing the reasoning capabilities of Large Language Models (LLMs). While prior re…
Compound photon blockade based on three mode system
Hongyu Lin
Based on the four wave mixing, a three mode nonlinear system is proposed. The single photon blockade is discussed through analytical analysis and numerical calculation. The analyti…
Denoising Distantly Supervised Named Entity Recognition via a Hypergeometric Probabilistic Model
Wenkai Zhang, Hongyu Lin, Xianpei Han +4
Denoising is the essential step for distant supervision based named entity recognition. Previous denoising methods are mostly based on instance-level confidence statistics, which i…
DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation
Hao Zheng, Guozhao Mo, Xinru Yan +7
Presentation generation requires deep content research, coherent visual design, and iterative refinement based on observation. However, existing presentation agents often rely on p…
Toward Unified Controllable Text Generation via Regular Expression Instruction
Xin Zheng, Hongyu Lin, Xianpei Han +1
Controllable text generation is a fundamental aspect of natural language generation, with numerous methods proposed for different constraint types. However, these approaches often…
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…
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…
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…
MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning
Qianhao Yuan, Jie Lou, Zichao Li +6
LLM-based search agents often concatenate the full interaction history into the context, producing long and noisy inputs, and increasing compute cost and GPU memory overhead. To ad…
Large Language Models Often Say One Thing and Do Another
Ruoxi Xu, Hongyu Lin, Xianpei Han +4
As large language models (LLMs) increasingly become central to various applications and interact with diverse user populations, ensuring their reliable and consistent performance i…
Tunable photon blockade in a two-mode second-order nonlinear system embedded with a two-level atom
Hongyu Lin, Xiangyi Luo, Hui Yang +1
The conventional photon blockade for high-frequency mode is investigated in a two-mode second-order nonlinear system embedded with a two-level atom. By solving the master equation…
READoc: A Unified Benchmark for Realistic Document Structured Extraction
Zichao Li, Aizier Abulaiti, Yaojie Lu +5
Document Structured Extraction (DSE) aims to extract structured content from raw documents. Despite the emergence of numerous DSE systems, their unified evaluation remains inadequa…
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…
Seg2Act: Global Context-aware Action Generation for Document Logical Structuring
Zichao Li, Shaojie He, Meng Liao +6
Document logical structuring aims to extract the underlying hierarchical structure of documents, which is crucial for document intelligence. Traditional approaches often fall short…