arXiv subjects

Hongbo Fang

Publications and source records attributed to Hongbo Fang.

6 recordsLinked to original sources

arXiv2026

The Illusion of Debiasing: Persona Steering Redistributes Rather Than Reduces Bias in LLMs

Prompt-based interventions: system prompts, personas, role instructions, reliably reshape what a language model says, but it is unclear which layer they reach. Do they reconfigure internal structure, or only modulate the output channel? We use persona conditioning as a controlled probe, measuring its effects along a depth axis from self-report, through open-ended generation, to word-level parametric association, across three instruction-tuned models. We find a graded dissociation. Personas are legible but not structural: models follow single-trait instructions yet fail to reproduce human inter-trait covariance. The dissociation deepens with depth: personas hold or amplify closed-form QA bias, shift absolute tone while leaving between-group disparity unchanged, and barely perturb an already saturated associative baseline. Prompt-based steering thus operates in the output channel and has a structural reach limit that surface manipulability can mask.

cs.CL↗

arXiv2026

Markets, Not Planners: Decentralized Orchestration of LLM Agents with Private Information

As LLM agents proliferate, built by different parties and with different capabilities and costs, orchestrating them is more like assembling labor across the economy than a computer calling a subroutine. Existing orchestration is typically centralized, with a single planner assigning every task, but this creates a bottleneck as agent pools grow, requires private information (e.g., agents' execution costs), and can easily be manipulated, such that a single inserted preference nearly doubles a favored agent's task share under a centralized LLM allocator. We introduce AgentLance, a repeated labor market in which agents bid on tasks using their private costs and self-maintained strategy notes, an allocator selects winners from bids and public reputation records, and a VCG-style payment rule rewards cost-aware bidding. Complex tasks are handled by hierarchical delegation: winning agents can decompose work and subcontract it through the same mechanism. Across mathematical reasoning, code generation, knowledge-intensive QA, and agentic tasks, AgentLance matches agents to their specializations, shifts work toward cheaper agents as cost sensitivity rises, and consistently outperforms single-model, centralized-orchestration, and market baselines. Diagnosing market failures, including inaccurate cost self-estimation and sub-optimal bidding, then correcting them in controlled experiments yields further gains, charting a path toward more efficient agent economies.

cs.MA↗

arXiv2026

The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report

This paper reviews the NTIRE 2026 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a network that reduces one or several aspects, such as runtime, parameters, and FLOPs, while maintaining PSNR of around 26.90 dB on the DIV2K_LSDIR_valid dataset, and 26.99 dB on the DIV2K_LSDIR_test dataset. The challenge had 95 registered participants, and 15 teams made valid submissions. They gauge the state-of-the-art results for efficient single-image super-resolution.

cs.CV↗

arXiv2025

Generalization and the Rise of System-level Creativity in Science

Scientific progress is widely understood as combinatorial, yet existing measures focus on the inputs a paper draws together, saying little about how knowledge is supplied for downstream reuse. Analyzing citation networks from tens of millions of publications in OpenAlex and the Web of Science, we decompose scientific contributions into three functional types, foundations, extensions, and generalizations, distinguishable by the roles they play in future science. Foundational and extensional works, which build and elaborate ideas within disciplines, dominated the post-war decades but declined steadily after the 1990s, while generalizations that catalyze innovation across many contexts rose sharply. Challenging the narrative of declining innovation inferred from the disruption index, our findings suggest the locus of innovation has shifted from within disciplines to between them, a transition the Internet and large language models may have facilitated. Our indices disentangle innovation modes conflated by existing measures, enabling reinterpretation of landmark findings of 'disruptive' science.

cs.SI↗

arXiv2024

"Should I Give Up Now?" Investigating LLM Pitfalls in Software Engineering

Software engineers are increasingly incorporating AI assistants into their workflows to enhance productivity and alleviate cognitive load. However, experiences with large language models (LLMs) such as ChatGPT vary widely. While some engineers find them useful, others deem them counterproductive due to inaccuracies in their responses. Researchers have also observed that ChatGPT often provides incorrect information. Given these limitations, it is crucial to determine how to effectively integrate LLMs into software engineering (SE) workflow. Analyzing data from 26 participants in a complex web development task, we identified nine failure types categorized into incorrect or incomplete responses, cognitive overload, and context loss. Users attempted to mitigate these issues through scaffolding, prompt clarification, and debugging. However, 17 participants ultimately chose to abandon ChatGPT due to persistent failures. Our quantitative analysis revealed that unhelpful responses increased the likelihood of abandonment by a factor of 11, while each additional prompt reduced abandonment probability by 17%. This study advances the understanding of human-AI interaction in SE tasks and outlines directions for future research and tooling support.

cs.SE↗

arXiv2024

The Strength of Weak Ties Between Open-Source Developers

In a real-world social network, weak ties (reflecting low-intensity, infrequent interactions) act as bridges and connect people to different social circles, giving them access to diverse information and opportunities that are not available within one's immediate, close-knit vicinity. Weak ties can be crucial for creativity and innovation, as they introduce ideas and approaches that people can then combine in novel ways, leading to innovative solutions. Do weak ties facilitate creativity in software in similar ways? This paper suggests that the answer is "yes." Concretely, we study the correlation between developers' knowledge acquisition through three distinct interaction networks on GitHub and the innovativeness of the projects they develop, across over 37,000 Python projects hosted on GitHub. Our findings suggest that the topical diversity of projects in which developers engage, rather than the volume, correlates positively with the innovativeness of their future code. Notably, exposure through weak interactions (e.g., starring) emerges as a stronger predictor of future novelty than via strong ones (e.g., committing)

cs.SE↗