@misc{fisher_guardrail,
  title = {Whose Guardrail? User Identity Shapes the Effectiveness of Model Disclaimers in Mitigating LLM Political Persuasion},
  author = {Jillian Fisher and Daniel W. Fisher and Thomas Richardson and Jennifer Pan and Yulia Tsvetkov and Katharina Reinecke},
  year = {2026},
  note = {arXiv:2611.05347},
  url = {https://arxiv.org/pdf/2611.05347}
}

Politically biased AI can shift users' opinions, yet it remains unclear whether model disclaimers protect against such persuasion. We report a preregistered experiment (N=1,586) examining how disclaimer design and user characteristics shape susceptibility to politically biased AI. We varied whether disclaimers identified political bias versus potential inaccuracies and whether they included an explanation. Participants completed two decision-making tasks with an LLM biased against their political views, with outcomes assessed immediately and one week later. Disclaimers identifying political bias and including an explanation reduced persuasion, but effects varied across contexts and did not persist. Individual differences were more consistent predictors: Republicans were more persuaded and reported higher trust than Democrats across tasks. Similarly, participants who used AI more frequently were also more persuaded, whereas those with greater self-reported AI knowledge were less persuaded. These findings suggest that generic disclaimers are not enough: effective safeguards must account for user heterogeneity and context.

@misc{wilde_newsbench,
  title = {NewsBench: Expert-Grounded Evaluation of Epistemic Quality in AI News Reporting},
  author = {Matt Wilde and Jillian Fisher and Andrew B. Hall and Kathryn Salam and Robbie Goldfarb},
  year = {2026},
  note = {arXiv:2610.33240},
  url = {https://byforum.com/whitepaper-files/newsbench.pdf}
}

As frontier AI systems increasingly serve as sources of political and current-events information, evaluating the epistemic quality of their responses is now especially consequential. Existing evaluations often focus narrowly on ideological alignment, rely on measures not validated for this setting, or depend on reference labels derived from public opinion or non-expert annotation, potentially producing misleading or miscalibrated results. To address these limitations, we introduce NewsBench, an expert-grounded benchmark that reframes evaluation around editorial standards developed by senior practitioners in journalism, policy, and intelligence analysis. NewsBench operationalizes quality across three dimensions, source quality, factuality, and neutrality, using a two-phase pipeline in which domain experts first define and calibrate evaluation guidelines, which are then transferred to automated AI judges validated against expert-adjudicated gold labels. The benchmark includes approximately 3,000 evaluation prompts, with roughly 500 refreshed monthly to capture emerging current events, roughly 2,500 human expert-annotated items for calibration and validation, and a suite of AI judges designed to enable scalable evaluation. To validate our methodology, we report both inter-rater reliability among human experts and AI judge–human agreement across all three dimensions. Finally, we apply NewsBench to four frontier models, revealing distinct and non-overlapping failure profiles in sourcing, factuality, and neutrality.

@inproceedings{fisher_rums,
  title = {Response-Aware User Memory Selection for LLM Personalization},
  author = {Jillian Fisher and Jennifer Neville and Chan Young Park},
  booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
  year = {2026},
  url = {https://aclanthology.org/2026.emnlp-main.185.pdf}
}

A common approach to personalization in large language models (LLMs) is to incorporate a subset of the user memory into the prompt at inference time to guide the model's generation. Existing methods select these subsets primarily using similarity between user memory items and input queries, ignoring how features actually affect the model's response distribution. We propose Response-Utility optimization for Memory Selection (RUMS), a novel method that selects user memory items by measuring the mutual information between a subset of memory and the model's outputs, identifying items that reduce response uncertainty and sharpen predictions beyond semantic similarity. We demonstrate that this information-theoretic foundation enables more principled user memory selection that aligns more closely with human selection compared to state-of-the-art methods, and models 400× larger. Additionally, we show that memory items selected using RUMS result in better response quality compared to existing approaches, while having up to 95% reduction in computational cost.

@unpublished{fisher_spectrum,
  title = {Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability},
  author = {Taylor Sorensen and Benjamin Newman and Jared Moore and Chan Park and Jillian Fisher and Niloofar Mireshghallah and Liwei Jiang and Yejin Choi},
  year = {2025},
  journal = {ICLR},
  file = {spectrum_tuning.pdf}
}

Language model post-training has enhanced instruction-following and performance on many downstream tasks, but also comes with an often-overlooked cost on tasks with many possible valid answers. We characterize three desiderata for conditional distributional modeling: in-context steerability, valid output space coverage, and distributional alignment, and document across three model families how current post-training can reduce these properties. In particular, we disambiguate between two kinds of in-context learning: ICL for eliciting existing underlying knowledge or capabilities, and in-context steerability, where a model must use in-context information to override its priors and steer to a novel data generating distribution. To better evaluate and improve these desiderata, we introduce Spectrum Suite, a large-scale resource compiled from >40 data sources and spanning >90 tasks requiring models to steer to and match diverse distributions ranging from varied human preferences to numerical distributions and more. We find that while current post-training techniques help elicit underlying capabilities and knowledge, they hurt models' ability to flexibly steer in-context. To mitigate these issues, we propose Spectrum Tuning, a post-training method using Spectrum Suite to improve steerability and distributional coverage. We find that Spectrum Tuning often improves over pretrained models and their instruction-tuned counterparts, enhancing steerability, spanning more of the output space, and improving distributional alignment on held-out datasets.

@unpublished{fisher_vlm_friendly",
  title = {Making VLMs More Robot-Friendly: Self-Critical Distillation of Low-Level Procedural Reasoning},
  author = {Chan Young Park, Jillian Fisher, Marius Memmel, Dipika Khullar, Andy Yun, Abhishek Gupta, Yejin Choi}
  year = {2025},
  file = {vlm_2025.pdf}
}

Large language models (LLMs) have shown promise in robotic procedural planning, yet their human-centric reasoning often omits the low-level, grounded details needed for robotic execution. Vision-language models (VLMs) offer a path toward more perceptually grounded plans, but current methods either rely on expensive, large-scale models or are constrained to narrow simulation settings. We introduce SelfReVision, a lightweight and scalable self-improvement framework for vision-language procedural planning. SelfReVision enables small VLMs to iteratively critique, revise, and verify their own plans-without external supervision or teacher models-drawing inspiration from chain-of-thought prompting and self-instruct paradigms. Through this self-distillation loop, models generate higher-quality, execution-ready plans that can be used both at inference and for continued fine-tuning. Using models varying from 3B to 72B, our results show that SelfReVision not only boosts performance over weak base VLMs but also outperforms models 100X the size, yielding improved control in downstream embodied tasks.

@unpublished{fisher_political_neutrality",
  title = {Political Neutrality in AI is Impossible- But Here is How to Approximate it},
  author = {Jillian Fisher, Ruth E. Appel, Chan Young Park, Yujin Potter, Liwei Jiang, Taylor Sorensen, Shangbin Feng, Yulia Tsvetkov, Margaret E. Roberts, Jennifer Pan, Dawn Song, Yejin Choi},
  year = {2025},
  file = {political_neutrality_2025.pdf}
}

AI systems often exhibit political bias, influencing users’ opinions and decision-making. While political neutrality—defined as the absence of bias—is often seen as an ideal solution for fairness and safety, this position paper argues that true political neutrality is neither feasible nor universally desirable due to its subjective nature and the biases inherent in AI training data, algorithms, and user interactions. However, inspired by Joseph Raz’s philosophical insight that “neutrality [...] can be a matter of degree” (Raz, 1986), we argue that striving for some neutrality remains essential for promoting balanced AI interactions and mitigating user manipulation. Therefore, we use the term “approximation” of political neutrality to shift the focus from unattainable absolutes to achievable, practical proxies. We propose eight techniques for approximating neutrality across three levels of conceptualizing AI, examining their trade-offs and implementation strategies. In addition, we explore two concrete applications of these approximations to illustrate their practicality. Finally, we assess our framework on current large language models (LLMs) at the output level, providing a demonstration of how it can be evaluated. This work seeks to advance nuanced discussions of political neutrality in AI and promote the development of responsible, aligned language models.

@unpublished{bias_llm",
  title = {Biased LLMs Can Influence Political Decision-Making},
  author = {Jillian Fisher, Shangbin Feng, Robert Aron, Thomas Richardson, Yejin Choi, Daniel W. Fisher, Jennifer Pan, Yulia Tsvetkov, Katharina Reinecke},
  year = {2023},
  note = {https://aclanthology.org/2025.acl-long.328/},
  file = {bias_llm.pdf}
}

As modern AI models become integral to everyday tasks, concerns about their inherent biases and their potential impact on human decision-making have emerged. While bias in models are well-documented, less is known about how these biases influence human decisions. This paper presents two interactive experiments investigating the effects of partisan bias in AI language models on political decision-making. Participants interacted freely with either a biased liberal, conservative, or unbiased control model while completing political decision-making tasks. We found that participants exposed to politically biased models were significantly more likely to adopt opinions and make decisions aligning with the AI’s bias, regardless of their personal political partisanship. However, we also discovered that prior knowledge about AI could lessen the impact of the bias, highlighting the possible importance of AI education for robust bias mitigation. Our findings not only highlight the critical effects of interacting with biased AI and its ability to impact public discourse and political conduct, but also highlights potential techniques for mitigating these risks in the future.

@unpublished{infoguided,
    title={Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models}, 
    author={Abhilasha Ravichander and Jillian Fisher and Taylor Sorensen and Ximing Lu and Yuchen Lin and Maria Antoniak and Niloofar Mireshghallah and Chandra Bhagavatula and Yejin Choi},
    journal = {NAACL}
  year = {2025},
  note = {https://arxiv.org/pdf/2503.12072},
  file = {guided_info.pdf}
}

High-quality training data has proven crucial for developing performant large language models (LLMs). However, commercial LLM providers disclose few, if any, details about the data used for training. This lack of transparency creates multiple challenges: it limits external oversight and inspection of LLMs for issues such as copyright infringement, it undermines the agency of data authors, and it hinders scientific research on critical issues such as data contamination and data selection. How can we re- cover what training data is known to LLMs? In this work we demonstrate a new method to identify training data known to proprietary LLMs like GPT-4 without requiring any access to model weights or token probabilities, by using information-guided probes. Our work builds on a key observation: text passages with high surprisal are good search material for memorization probes. By evaluating a model’s ability to successfully reconstruct high-surprisal tokens in text, we can identify a surprising number of texts memorized by LLMs.

@unpublished{styleremix,
  title = {StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements},
  author = {Jillian Fisher, Skyler Hallinan, Ximing Lu, Mitchell Gordon, Zaid Harchaoui, Yejin Choi},
  journal = {EMNLP}
  year = {2024},
  note = {https://aclanthology.org/2024.emnlp-main.241/},
  file = {styleremix.pdf}
}

Authorship obfuscation, rewriting a text to intentionally obscure the identity of the author, is an important but challenging task. Current methods using large language models (LLMs) lack interpretability and controllability, often ignoring author-specific stylistic features, resulting in less robust performance overall.
    To address this, we develop StyleRemix, an adaptive and interpretable obfuscation method that perturbs specific, fine-grained style elements of the original input text. StyleRemix uses pre-trained Low Rank Adaptation (LoRA) modules to rewrite an input specifically along various stylistic axes (e.g., formality and length) while maintaining low computational cost. StyleRemix outperforms state-of-the-art baselines and much larger LLMs in a variety of domains as assessed by both automatic and human evaluation.
    Additionally, we release AuthorMix, a large set of 30K high-quality, long-form texts from a diverse set of 14 authors and 4 domains, and DiSC, a parallel corpus of 1,500 texts spanning seven style axes in 16 unique directions.

@unpublished{modular_pluralism,
  title = {Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration},
  author = {Shangbin Feng, Taylor Sorensen, Yuhan Liu, Jillian Fisher, Chan Young Park, Yejin Choi, Yulia Tsvetkov},
  journal = {EMNLP},
  year = {2024},
  note = {https://aclanthology.org/2024.emnlp-main.240/},
  file = {modular_pluralism.pdf}
}

While existing alignment paradigms have been integral in developing large language models (LLMs), LLMs often learn an averaged human preference and struggle to model diverse preferences across cultures, demographics, and communities. We propose Modular Pluralism, a modular framework based on multi-LLM collaboration for pluralistic alignment: it "plugs into" a base LLM a pool of smaller but specialized community LMs, where models collaborate in distinct modes to flexibility support three modes of pluralism: Overton, steerable, and distributional. Modular Pluralism is uniquely compatible with black-box LLMs and offers the modular control of adding new community LMs for previously underrepresented communities. We evaluate Modular Pluralism with six tasks and four datasets featuring questions/instructions with value-laden and perspective-informed responses. Extensive experiments demonstrate that Modular Pluralism advances the three pluralism objectives across six black-box and open-source LLMs. Further analysis reveals that LLMs are generally faithful to the inputs from smaller community LLMs, allowing seamless patching by adding a new community LM to better cover previously underrepresented communities.

@unpublished{pluralism_roadmap,
  title = {A Roadmap to Pluralistic Alignment},
  author = {Sorensen, Taylor and Moore, Jared and Fisher, Jillian and Gordon, Mitchell and Mireshghallah, Niloofar and Rytting, Christopher Michael and Ye, Andre and Jiang, Liwei and Lu, Ximing and Dziri, Nouha and Althoff, Tim and Choi, Yejin},
  journal = {ICML},
  year = {2024},
  note = {https://dl.acm.org/doi/10.5555/3692070.3693952},
  file = {roadmap_to_pluralistic_alignment.pdf}
}

With increased power and prevalence of AI systems, it is ever more critical that AI systems are designed to serve all, i.e., people with diverse values and perspectives. However, aligning models to serve pluralistic human values remains an open research question. In this piece, we propose a roadmap to pluralistic alignment, specifically using language models as a test bed. We identify and formalize three possible ways to define and operationalize pluralism in AI systems: 1) Overton pluralistic models that present a spectrum of reasonable responses; 2) Steerably pluralistic models that can steer to reflect certain perspectives; and 3) Distributionally pluralistic models that are well-calibrated to a given population in distribution. We also propose and formalize three possible classes of pluralistic benchmarks: 1) Multi-objective benchmarks, 2) Trade-off steerable benchmarks, which incentivize models to steer to arbitrary trade-offs, and 3) Jury-pluralistic benchmarks which explicitly model diverse human ratings. We use this framework to argue that current alignment techniques may be fundamentally limited for pluralistic AI; indeed, we highlight empirical evidence, both from our own experiments and from other work, that standard alignment procedures might reduce distributional pluralism in models, motivating the need for further research on pluralistic alignment.

@unpublished{author_obf,
  author = {Fisher, Jillian and Lu, Ximing and Jung, Jaehun and Jiang, Liwei and Choi, Yejin},
  title = {JAMDEC: Unsupervised Authorship Obfuscation using Contrained Decoding over Small Language Models},
  journal = {NAACL},
  note = {https://aclanthology.org/2024.naacl-long.87/},
  file = {JAMDEC.pdf},
  year = {2024}
}

The permanence of online content combined with the enhanced authorship identification techniques calls for stronger computational methods to protect the identity and  privacy of online authorship when needed, e.g., blind reviews for scientific papers, anonymous online reviews, or anonymous interactions in the mental health forums. In this paper, we propose an unsupervised inference-time approach to authorship obfuscation to address the unique challenges of authorship obfuscation: lack of supervision data for diverse authorship and domains, and the need for a sufficient level of revision beyond simple paraphrasing to obfuscate the authorship, all the while preserving the original content and fluency. We introduce MASQUERADE Decoding, a  user-controlled, inference-time algorithm for authorship obfuscation that can be in principle applied to any text and authorship. Our approach builds on small language models such as GPT2-XL in order to help avoid disclosing the original content to proprietary LLM’s APIs, while also reducing the performance gap between small and large language models via algorithmic enhancement. The key idea behind our approach is to boost the creative power of smaller language models through constrained decoding, while also allowing for user-specified controls and flexibility. Experimental results demonstrate that our approach based on GPT2-XL outperforms previous state-of-the-art methods based on comparably small models, while performing competitively against GPT3 175B, a propriety model that is two orders of magnitudes larger. 

@inproceedings{generative_paradox,
  author = {West, Peter and Lu, Ximing and Dziri, Nouha and Brahman, Faeze and Li, Linjie and Hwang, Jena D. and Jiang, Liwei and Fisher, Jillian and Ravichander, Abhilasha and Chandu, Khyathi and Newman, Benjamin and Koh, Pang Wei and Ettinger, Allyson and Choi, Yejin},
  title = {The Generative AI Paradox: "What It Can Create, It May Not Understand"},
  year = {2024},
  note = {https://arxiv.org/abs/2311.000595},
  file = {generation_paradox.pdf},
  month = dec,
  address = {Vienna},
  publisher = {International Conference on Learning Representations (ICLR)}
}

The recent wave of generative AI has sparked unprecedented global attention, with both excitement and concern over potentially superhuman levels of artifi- cial intelligence: models now take only seconds to produce outputs that would challenge or exceed the capabilities even of expert humans. At the same time, models still show basic errors in understanding that would not be expected even in non-expert humans. This presents us with an apparent paradox: how do we rec- oncile seemingly superhuman capabilities with the persistence of errors that few humans would make? In this work, we posit that this tension reflects a divergence in the configuration of intelligence in today’s generative models relative to intel- ligence in humans. Specifically, we propose and test the Generative AI Paradox hypothesis: generative models, having been trained directly to reproduce expert- like outputs, acquire generative capabilities that are not contingent upon—and can therefore exceed—their ability to understand those same types of outputs. This contrasts with humans, for whom basic understanding almost always precedes the ability to generate expert-level outputs. We test this hypothesis through controlled experiments analyzing generation vs. understanding in generative models, across both language and image modalities. Our results show that although models can outperform humans in generation, they consistently fall short of human capabili- ties in measures of understanding, showing weaker correlation between generation and understanding performance, and more brittleness to adversarial inputs. Our findings support the hypothesis that models’ generative capability may not be con- tingent upon understanding capability, and call for caution in interpreting artificial intelligence by analogy to human intelligence.

@inproceedings{influence_theory,
  title = {Statistical and Computational Guarantees for Influence Diagnostics},
  author = {Fisher, Jillian and Liu, Lang and Pillutla, Krishna and Choi, Yejin and Harchaoui, Zaid},
  year = {2023},
  month = apr,
  address = {Valencia},
  publisher = {Artificial Intelligence and Statistics (AISTATS)},
  doi = {10.48550/arXiv.2212.04014},
  note = {https://arxiv.org/pdf/2212.04014.pdf},
  primaryclass = {stat.ML},
  file = {influence_theory.pdf}
}

Influence diagnostics such as influence functions and approximate maximum influence perturba- tions are popular in machine learning and in AI domain applications. Influence diagnostics are powerful statistical tools to identify influential datapoints or subsets of datapoints. We establish finite-sample statistical bounds, as well as com- putational complexity bounds, for influence func- tions and approximate maximum influence per- turbations using efficient inverse-Hessian-vector product implementations. We illustrate our results with generalized linear models and large attention based models on synthetic and real data.