11 citations · 20 across the 14 of their papers we have counts for
18 papers
LaVGuard: Selective Decoding for Contextual Value Drift
Jiale Dai, Liuxian Ma, Hongcan Deng +5
A content-safe response can still promote priorities that conflict with its task: an assistant may demand compliance when asked to preserve autonomy. We study contextual value drif…
Values as Style: Disentangling Values from Semantics with One-Way Mixing for Low-Damage LLM Steering
Jiale Dai, Hongcan Deng, Liuxian Ma +2
Value steering should change an LLM's normative priorities while preserving the scenario, facts, and task constraints underlying its answer. Conventional activation edits often cha…
VISTA: Value-Informed Event Appraisal for Multimodal Emotion Conflict
Jiale Dai, Liuxian Ma, Xiaoke Niu +5
Conflicting emotional cues can be individually valid: a subdued voice may reflect a blocked goal while a smile satisfies a social obligation. Their interpretation depends on what t…
Harness-Zero: Harness Distillation via Agent-as-Harness
Haoran Ye, Yuxing Lu, Haonan Dong +2
Agent harnesses, the external systems that mediate model-environment interaction, can substantially improve agent performance, but their gains remain tied to the harness at deploym…
Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance
Wenhao Chen, Sirui Sun, Shengyuan Bai +1
Aligning large language models (LLMs) with human values typically relies on post-training or inference-time steering that directly manipulates the backbone's parameters or represen…
Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values
Haonan Dong, Qiguan Feng, Kehan Jiang +3
Autonomous agents have rapidly matured as task executors and seen widespread deployment via harnesses such as OpenClaw. Safety concerns have rightly drawn growing research attentio…
Context-Value-Action Architecture for Value-Driven Large Language Model Agents
TianZe Zhang, Sirui Sun, Yuhang Xie +3
Large Language Models (LLMs) have shown promise in simulating human behavior, yet existing agents often exhibit behavioral rigidity, a flaw frequently masked by the self-referentia…
NeuReasoner: Towards Explainable, Controllable, and Unified Reasoning via Mixture-of-Neurons
Haonan Dong, Kehan Jiang, Haoran Ye +3
Large Reasoning Models (LRMs) have recently achieved remarkable success in complex reasoning tasks. However, closer scrutiny reveals persistent failure modes compromising performan…
FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models
Kehan Jiang, Haonan Dong, Zhaolu Kang +2
Recent Large Reasoning Models (LRMs) like DeepSeek-R1 have demonstrated remarkable success in complex reasoning tasks, exhibiting human-like patterns in exploring multiple alternat…
Meta Context Engineering via Agentic Skill Evolution
Haoran Ye, Xuning He, Vincent Arak +2
The operational efficacy of large language models relies heavily on their inference-time context. This has established Context Engineering (CE) as a formal discipline for optimizin…
Evolutionary System 2 Reasoning: An Empirical Proof
Zeyuan Ma, Wenqi Huang, Guo-Huan Song +4
Machine intelligence marks the ultimate dream of making machines' intelligence comparable to human beings. While recent progress in Large Language Models (LLMs) show substantial sp…
Meta-R1: Empowering Large Reasoning Models with Metacognition
Haonan Dong, Haoran Ye, Wenhao Zhu +2
Large Reasoning Models (LRMs) demonstrate remarkable capabilities on complex tasks, exhibiting emergent, human-like thinking patterns. Despite their advances, we identify a fundame…
EAVIT: Efficient and Accurate Human Value Identification from Text data via LLMs
Wenhao Zhu, Yuhang Xie, Guojie Song +1
The rapid evolution of large language models (LLMs) has revolutionized various fields, including the identification and discovery of human values within text data. While traditiona…
Large Language Model Psychometrics: A Systematic Review of Evaluation, Validation, and Enhancement
Haoran Ye, Jing Jin, Yuhang Xie +2
The advancement of large language models (LLMs) has outpaced traditional evaluation methodologies. This progress presents novel challenges, such as measuring human-like psychologic…
Generative Psycho-Lexical Approach for Constructing Value Systems in Large Language Models
Haoran Ye, Tianze Zhang, Yuhang Xie +4
Values are core drivers of individual and collective perception, cognition, and behavior. Value systems, such as Schwartz's Theory of Basic Human Values, delineate the hierarchy an…
Measuring Human and AI Values Based on Generative Psychometrics with Large Language Models
Haoran Ye, Yuhang Xie, Yuanyi Ren +3
Human values and their measurement are long-standing interdisciplinary inquiry. Recent advances in AI have sparked renewed interest in this area, with large language models (LLMs)…
ValueBench: Towards Comprehensively Evaluating Value Orientations and Understanding of Large Language Models
Yuanyi Ren, Haoran Ye, Hanjun Fang +2
Large Language Models (LLMs) are transforming diverse fields and gaining increasing influence as human proxies. This development underscores the urgent need for evaluating value or…
ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
Haoran Ye, Jiarui Wang, Zhiguang Cao +5
The omnipresence of NP-hard combinatorial optimization problems (COPs) compels domain experts to engage in trial-and-error heuristic design. The long-standing endeavor of design au…