40 citations · 100 across the 68 of their papers we have counts for
73 papers
Repairing LLM-Generated Specifications with Deterministic Diagnosis
Giovanni Vaccarino, Emanuele La Malfa, Dehai Min +6
Large language models (LLMs) are increasingly used as formalizers: given a reasoning problem expressed in natural language, they produce a formal specification that a symbolic solv…
ATLAS: Aligned Transport of Latent Structure for Reliable World Model Planning
Ke Fang, Yupu Yao, Lu Cheng
Latent world models rely on representation geometry for planning, yet regularizing the latent marginal alone does not determine the state-to-state relationships used for action sel…
Escaping Reasoning Basin Collapse with History-Biased Search
Lu Cheng
Inference-time search with large language models (LLMs) often concentrates on a small set of structurally or semantically similar trajectories, leaving alternative reasoning strate…
TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning
Fangxu Yu, Tao Feng, Dehai Min +3
Time series reasoning is essential for real-world problem-solving. While both Large Language Models (LLMs) and Vision-Language Models (VLMs) can reason about time-series data, thei…
Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator
Shiping Yang, Shining Liang, Weihao Liu +4
Identifying faithfulness hallucinations in LLM-generated outputs remains challenging due to the scarcity of high-quality annotated data. Recent work relies on advanced LLMs to synt…
Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution
Xiaoou Liu, Tiejin Chen, Dengjia Zhang +3
Large Language Models have achieved strong performance on reasoning tasks with objective answers by generating step-by-step solutions, but diagnosing where a multi-step reasoning t…
One Skill, Two Masters: Serving Users and Attackers through Skill Injection
Haochang Hao, Dehai Min, Zhifang Zhang +5
Large language model agents use skills that package reusable instructions, code, and resources. Existing skill-injection attacks exploit trust in these packages by adding malicious…
Beyond Math and Code: Lightweight Corpus-Grounded Process Rewards for Factual Question Answering
Shicheng Fan, Haochang Hao, Dehai Min +10
Process supervision during reinforcement learning (RL) post-training matters in factual question answering (QA) because responses receiving positive response-level rewards can stil…
Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models
Dehai Min, Giovanni Vaccarino, Huiyi Chen +3
Large Reasoning Models (LRMs) achieve strong performance by generating long chains of thought (CoT), but often overthink, continuing to reason after a solution has already stabiliz…
FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale
Runyuan He, Qiuyang Mang, Shang Zhou +14
Many real-world coding challenges are open-ended and admit no known optimal solution. Yet, recent progress in LLM coding has focused on well-defined tasks such as feature implement…
MOSAIC: Module Discovery via Sparse Additive Identifiable Causal Learning for Scientific Time Series
Shicheng Fan, Nour Elhendawy, Jianle Sun +4
Causal representation learning (CRL) seeks to recover latent variables with identifiability guarantees, typically up to permutation and component-wise reparameterization under appr…
LLM-Guided Safety Agent for Edge Robotics with an ISO-Compliant Perception-Compute-Control Architecture
Xu Huang, Ruofan Zhang, Lu Cheng +8
Ensuring functional safety in human-robot interaction is challenging because AI perception is inherently probabilistic, whereas industrial standards require deterministic behavior.…
Differentiable Conformal Training for LLM Reasoning Factuality
Nathan Hittesdorf, Marco Salzetta, Lu Cheng
Large Language Models (LLMs) frequently hallucinate, limiting their reliability in critical applications. Conformal Prediction (CP) addresses this by calibrating error rates on hel…
Adaptive Stopping for Multi-Turn LLM Reasoning
Xiaofan Zhou, Huy Nguyen, Bo Yu +2
Large Language Models (LLMs) increasingly rely on multi-turn reasoning and interaction, such as adaptive retrieval-augmented generation (RAG) and ReAct-style agents, to answer diff…
A Novel Multi-Agent Architecture to Reduce Hallucinations of Large Language Models in Multi-Step Structural Modeling
Ziheng Geng, Jiachen Liu, Ran Cao +3
Large language models (LLMs) such as GPT and Gemini have demonstrated remarkable capabilities in contextual understanding and reasoning. The strong performance of LLMs has sparked…
URAG: A Benchmark for Uncertainty Quantification in Retrieval-Augmented Large Language Models
Vinh Nguyen, Cuong Dang, Jiahao Zhang +6
Retrieval-Augmented Generation (RAG) has emerged as a widely adopted approach for enhancing LLMs in scenarios that demand extensive factual knowledge. However, current RAG evaluati…
SELAUR: Self Evolving LLM Agent via Uncertainty-aware Rewards
Dengjia Zhang, Xiaoou Liu, Lu Cheng +3
Large language models (LLMs) are increasingly deployed as multi-step decision-making agents, where effective reward design is essential for guiding learning. Although recent work e…
Context-Aware Counterfactual Data Augmentation for Gender Bias Mitigation in Language Models
Shweta Parihar, Liu Guangliang, Natalie Parde +1
A challenge in mitigating social bias in fine-tuned language models (LMs) is the potential reduction in language modeling capability, which can harm downstream performance. Counter…
Evaluating Social Bias in RAG Systems: When External Context Helps and Reasoning Hurts
Shweta Parihar, Lu Cheng
Social biases inherent in large language models (LLMs) raise significant fairness concerns. Retrieval-Augmented Generation (RAG) architectures, which retrieve external knowledge so…
When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification
Jiale Zhao, Ke Fang, Lu Cheng
Large language models (LLMs) often respond even when prompts omit critical details or include misleading information, leading to hallucinations or reinforced misconceptions. We stu…
Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens
Weihao Liu, Dehai Min, Lu Cheng
While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it constrains the model's thoughts to a discrete vocabulary space. Rec…
TRACE: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learning
Shicheng Fan, Kun Zhang, Lu Cheng
Temporal causal representation learning methods assume that causal mechanisms switch instantaneously between discrete domains, yet real-world systems often exhibit continuous mecha…
EpiQAL: Benchmarking Large Language Models in Epidemiological Question Answering and Reasoning
Mingyang Wei, Dehai Min, Zewen Liu +8
Reliable epidemiological reasoning requires synthesizing study evidence to infer disease burden, transmission dynamics, and intervention effects at the population level. Existing m…
FrontierCS: Evolving Challenges for Evolving Intelligence
Qiuyang Mang, Wenhao Chai, Zhifei Li +48
We introduce FrontierCS, a benchmark of 156 open-ended problems across diverse areas of computer science, designed and reviewed by experts, including CS PhDs and top-tier competiti…