Author name cluster

Weiyan Shi

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

2 author rows

TMLR Journal 2026 Journal Article

SocialFusion: Addressing Social Degradation in Pre-trained Vision-Language Models

Hamza Tahboub
Weiyan Shi
Gang Hua
Huaizu Jiang

Understanding social interactions from visual cues is a fundamental challenge for a socially competent AI. While powerful pre-trained vision-language models (VLMs) have shown remarkable general capabilities, they surprisingly struggle to unify and learn multiple social perception tasks simultaneously, often exhibiting negative transfer. We identify that this negative transfer stems from a critical issue we term "social degradation," whereby the general visual-linguistic pre-training process of VLMs impairs the visual encoder's ability to represent nuanced social information. We investigate this behavior further under two lenses: decodability through linear representation probing and compatibility through gradient conflict analysis, revealing that both play a role in the degradation, especially the former, which is significantly compromised in the VLM pre-training process. To address these issues, we propose SocialFusion, a unified framework that learns a minimal connection between a frozen visual encoder and a language model. Compared with existing VLMs, it exhibits positive transfer across all five social tasks, leveraging synergies between them to enhance overall performance and achieves comparable performance to task-specific state-of-the-art models on various benchmarks. Our findings suggest that current VLM pre-training strategies may be detrimental to acquiring general social competence and highlight the need for more socially-aware training paradigms.

PDF Details

NeurIPS Conference 2025 Conference Paper

LLMs Encode Harmfulness and Refusal Separately

Jiachen Zhao
Jing Huang
Zhengxuan Wu
David Bau
Weiyan Shi

LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing? Prior work has shown that LLMs’ refusal behaviors can be mediated by a one-dimensional subspace, i. e. , a refusal direction. In this work, we identify a new dimension to analyze safety mechanisms in LLMs, i. e. , harmfulness, which is encoded internally as a separate concept from refusal. And there exists a harmfulness direction that is distinct from the refusal direction. As causal evidence, steering along the harmfulness direction can lead LLMs to interpret harmless instructions as harmful, but steering along the refusal direction tends to elicit refusal responses directly without reversing the model’s judgment on harmfulness. Furthermore, using our identified harmfulness concept, we find that certain jailbreak methods work by reducing the refusal signals without suppressing the model’s internal belief of harmfulness. We also find that adversarially fine- tuning models to accept harmful instructions has minimal impact on the model’s internal belief of harmfulness. These insights lead to a practical safety application: The model’s latent harmfulness representation can serve as an intrinsic safeguard (Latent Guard) for detecting unsafe inputs and reducing over-refusals that is robust to finetuning attacks. For instance, our Latent Guard achieves performance comparable to or better than Llama Guard 3 8B, a dedicated finetuned safeguard model, across different jailbreak methods. Our findings suggest that LLMs’ internal understanding of harmfulness is more robust than their refusal decision to diverse input instructions, offering a new perspective to study AI safety.

PDF Details

AAAI Conference 2025 Conference Paper

Persuasion for Social Good: How to Build and Break AI

Weiyan Shi

Persuasion is important in numerous situations like healthy habit promotion, and emotional support. As AI gets more involved in our daily life, it becomes critical to study how they can persuade humans and how persuasive they are. In this talk, I will cover (1) how to build such persuasive AI systems that can persuade, negotiate, and cooperate with other humans in the game of Diplomacy. (2) I will also discuss how humans perceive such specialized AI systems. This study validates the necessity of California's Autobot Law and proposes guidance to regulate such systems. (3) As these systems become more powerful, AI safety problems become more important. So I will describe how to persuade AI models to jailbreak them and study AI safety problems. Finally, I will conclude with my long-term vision to further study persuasion from a multi-angle approach that combines Artificial Intelligence, Human-Computer Interaction, and social sciences.

PDF Details DOI

ICML Conference 2024 Conference Paper

Position: A Safe Harbor for AI Evaluation and Red Teaming

Shayne Longpre
Sayash Kapoor
Kevin Klyman
Ashwin Ramaswami
Rishi Bommasani
Borhane Blili-Hamelin
Yangsibo Huang
Aviya Skowron

Independent evaluation and red teaming are critical for identifying the risks posed by generative AI systems. However, the terms of service and enforcement strategies used by prominent AI companies to deter model misuse have disincentives on good faith safety evaluations. This causes some researchers to fear that conducting such research or releasing their findings will result in account suspensions or legal reprisal. Although some companies offer researcher access programs, they are an inadequate substitute for independent research access, as they have limited community representation, receive inadequate funding, and lack independence from corporate incentives. We propose that major generative AI developers commit to providing a legal and technical safe harbor, protecting public interest safety research and removing the threat of account suspensions or legal reprisal. These proposals emerged from our collective experience conducting safety, privacy, and trustworthiness research on generative AI systems, where norms and incentives could be better aligned with public interests, without exacerbating model misuse. We believe these commitments are a necessary step towards more inclusive and unimpeded community efforts to tackle the risks of generative AI.

Details

NeurIPS Conference 2024 Conference Paper

PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action

Yijia Shao
Tianshi Li
Weiyan Shi
Yanchen Liu
Diyi Yang

As language models (LMs) are widely utilized in personalized communication scenarios (e. g. , sending emails, writing social media posts) and endowed with a certain level of agency, ensuring they act in accordance with the contextual privacy norms becomes increasingly critical. However, quantifying the privacy norm awareness of LMs and the emerging privacy risk in LM-mediated communication is challenging due to (1) the contextual and long-tailed nature of privacy-sensitive cases, and (2) the lack of evaluation approaches that capture realistic application scenarios. To address these challenges, we propose PrivacyLens, a novel framework designed to extend privacy-sensitive seeds into expressive vignettes and further into agent trajectories, enabling multi-level evaluation of privacy leakage in LM agents' actions. We instantiate PrivacyLens with a collection of privacy norms grounded in privacy literature and crowdsourced seeds. Using this dataset, we reveal a discrepancy between LM performance in answering probing questions and their actual behavior when executing user instructions in an agent setup. State-of-the-art LMs, like GPT-4 and Llama-3-70B, leak sensitive information in 25. 68% and 38. 69% of cases, even when prompted with privacy-enhancing instructions. We also demonstrate the dynamic nature of PrivacyLens by extending each seed into multiple trajectories to red-team LM privacy leakage risk. Dataset and code are available at https: //github. com/SALT-NLP/PrivacyLens.

PDF Details DOI

AAAI Conference 2020 Conference Paper

End-to-End Trainable Non-Collaborative Dialog System

Yu Li
Kun Qian
Weiyan Shi
Zhou Yu

End-to-end task-oriented dialog models have achieved promising performance on collaborative tasks where users willingly coordinate with the system to complete a given task. While in non-collaborative settings, for example, negotiation and persuasion, users and systems do not share a common goal. As a result, compared to collaborate tasks, people use social content to build rapport and trust in these non-collaborative settings in order to advance their goals. To handle social content, we introduce a hierarchical intent annotation scheme, which can be generalized to different non-collaborative dialog tasks. Building upon Transfer- Transfo (Wolf et al. 2019), we propose an end-to-end neural network model to generate diverse coherent responses. Our model utilizes intent and semantic slots as the intermediate sentence representation to guide the generation process. In addition, we design a ﬁlter to select appropriate responses based on whether these intermediate representations ﬁt the designed task and conversation constraints. Our noncollaborative dialog model guides users to complete the task while simultaneously keeps them engaged. We test our approach on our newly proposed ANTISCAM dataset and an existing PERSUASIONFORGOOD dataset. Both automatic and human evaluations suggest that our model outperforms multiple baselines in these two non-collaborative tasks.

PDF Details