Allison Koenecke
LightNews LightNews
allisonkoe.bsky.social
Allison Koenecke
@allisonkoe.bsky.social
2.6K followers 280 following 29 posts
asst prof @ cornell info sci | fairness in tech, public health & services | alum of MSR, Stanford ICME, NERA Econ, MIT Math | she/her | koenecke.infosci.cornell.edu
Posts Replies Media Videos
Reposted by Allison Koenecke
emmapierson.bsky.social
We have a new paper in Science Advances proposing a simple test for bias:

Is the same person treated differently when their race is perceived differently?

Specifically, we study: is the same driver likelier to be searched by police when they are perceived as Hispanic rather than white?

1/
November 24, 2025 at 6:14 PM
Reposted by Allison Koenecke
isabelcorpus.bsky.social
Had a great time at CODE@MIT this weekend, and wanted to highlight a few (of the many) cool talks!
November 18, 2025 at 2:54 PM
Reposted by Allison Koenecke
jennahgosciak.bsky.social
For day 5 of the #30daymapchallenge, I compared the original ecology of New York City with data from the Welikia Project to the present-day.
urban-data.bsky.social Urban Data @urban-data.bsky.social · 16d
We might be a few days delayed on the #30DayMapChallenge, but our day 5 submission spans almost 250 years of history! Our "Earth" map comes from @jennahgosciak.bsky.social, who compared the original ecology of New York City to present day variables.
November 11, 2025 at 5:38 PM
Reposted by Allison Koenecke
kpaxdonahue.bsky.social
I’m recruiting students this upcoming cycle at UIUC! I’m excited about Qs on societal impact of AI, especially human-AI collaboration, multi-agent interactions, incentives in data sharing, and AI policy/regulation (all from both a theoretical and applied lens). Apply through CS & select my name!
November 6, 2025 at 6:52 PM
Reposted by Allison Koenecke
kaitlynzhou.bsky.social
No better time to start learning about that #AI thing everyone's talking about...

📢 I'm recruiting PhD students in Computer Science or Information Science @cornellbowers.bsky.social!

If you're interested, apply to either department (yes, either program!) and list me as a potential advisor!
Photo of Cornelll University building surrounded by colorful trees
November 6, 2025 at 4:19 PM
allisonkoe.bsky.social
It was fantastic to collaborate across Cornell and Apple for our EMNLP paper auditing LLMs for dialectal biases in multiple choice benchmark datasets: arxiv.org/abs/2510.00962.

Anna @annaseogyeongchoi.bsky.social (who's on the job market this year!) did a great job presenting this work today!
November 6, 2025 at 1:17 AM
Reposted by Allison Koenecke
informor.bsky.social
Jobs! First, we hope to be hiring in Computer Science for the @cornelltech.bsky.social campus:

academicjobsonline.org/ajo/jobs/30804

Focus on security, SysML, and NLP.

Please share!
Cornell University, Computer Science
Job #AJO30804, Professor Positions - Computer Science, Cornell Tech, Computer Science, Cornell University, New York, New York, US
academicjobsonline.org
October 20, 2025 at 5:46 PM
Reposted by Allison Koenecke
angelinawang.bsky.social
Cornell (NYC and Ithaca) is recruiting AI postdocs, apply by Nov 20, 2025! If you're interested in working with me on technical approaches to responsible AI (e.g., personalization, fairness), please email me.

academicjobsonline.org/ajo/jobs/30971
Cornell University, Empire AI Fellows Program
Job #AJO30971, Postdoctoral Fellow, Empire AI Fellows Program, Cornell University, New York, New York, US
academicjobsonline.org
October 28, 2025 at 6:19 PM
Reposted by Allison Koenecke
dmimno.bsky.social
Cornell Information Science is hiring a Teaching Professor! Apply this week for full consideration:

academicjobsonline.org/ajo/jobs/30763
Cornell University, Information Science
Job #AJO30763, 2025-2026 CORNELL INFORMATION SCIENCE FULL-TIME TEACHING FACULTY SEARCH (OPEN-RANK TEACHING PROFESSOR), ITHACA CAMPUS  , Information Science, Cornell University, Ithaca, New York, US
academicjobsonline.org
October 28, 2025 at 1:12 PM
Reposted by Allison Koenecke
nkgarg.bsky.social
*Proud advisor moment* My (first) PhD student Zhi Liu (zhiliu724.github.io) is 1 of 4 finalists for the INFORMS Dantzig Dissertation Award, the premier dissertation award for the OR community. His dissertation spanned work with 2 NYC govt agencies, on measuring and mitigating operational inequities
Zhi Liu
About me
zhiliu724.github.io
August 28, 2025 at 4:58 PM
Reposted by Allison Koenecke
nkgarg.bsky.social
New piece, out in the Sigecom Exchanges! It's my first solo-author piece, and the closest thing I've written to being my "manifesto." #econsky #ecsky
arxiv.org/abs/2507.03600
Screenshot of paper abstract, with text: "A core ethos of the Economics and Computation (EconCS) community is that people have complex private preferences and information of which the central planner is unaware, but which an appropriately designed mechanism can uncover to improve collective decisionmaking. This ethos underlies the community’s largest deployed success stories, from stable matching systems to participatory budgeting. I ask: is this choice and information aggregation “worth it”? In particular, I discuss how such systems induce heterogeneous participation: those already relatively advantaged are, empirically, more able to pay time costs and navigate administrative burdens imposed by the mechanisms. I draw on three case studies, including my own work – complex democratic mechanisms, resident crowdsourcing, and school matching. I end with lessons for practice and research, challenging the community to help reduce participation heterogeneity and design and deploy mechanisms that meet a “best of both worlds” north star: use preferences and information from those who choose to participate, but provide a “sufficient” quality of service to those who do not."
August 11, 2025 at 1:25 PM
allisonkoe.bsky.social
@jennahgosciak.bsky.social just gave a fantastic talk on this paper about temporally missing data at @ic2s2.bsky.social 🎉 -- find us this afternoon if you want to chat about it!
jennahgosciak.bsky.social Jennah Gosciak @jennahgosciak.bsky.social · Jun 24
I am presenting a new 📝 “Bias Delayed is Bias Denied? Assessing the Effect of Reporting Delays on Disparity Assessments” at @facct.bsky.social on Thursday, with @aparnabee.bsky.social, Derek Ouyang, @allisonkoe.bsky.social, @marzyehghassemi.bsky.social, and Dan Ho. 🔗: arxiv.org/abs/2506.13735
(1/n)
"Bias Delayed is Bias Denied? Assessing the Effect of Reporting Delays on Disparity Assessments" Conducting disparity assessments at regular time intervals is critical for surfacing potential biases in decision-making and improving outcomes across demographic groups. Because disparity assessments fundamentally depend on the availability of demographic information, their efficacy is limited by the availability and consistency of available demographic identifiers. While prior work has considered the impact of missing data on fairness, little attention has been paid to the role of delayed demographic data. Delayed data, while eventually observed, might be missing at the critical point of monitoring and action -- and delays may be unequally distributed across groups in ways that distort disparity assessments. We characterize such impacts in healthcare, using electronic health records of over 5M patients across primary care practices in all 50 states. Our contributions are threefold. First, we document the high rate of race and ethnicity reporting delays in a healthcare setting and demonstrate widespread variation in rates at which demographics are reported across different groups. Second, through a set of retrospective analyses using real data, we find that such delays impact disparity assessments and hence conclusions made across a range of consequential healthcare outcomes, particularly at more granular levels of state-level and practice-level assessments. Third, we find limited ability of conventional methods that impute missing race in mitigating the effects of reporting delays on the accuracy of timely disparity assessments. Our insights and methods generalize to many domains of algorithmic fairness where delays in the availability of sensitive information may confound audits, thus deserving closer attention within a pipeline-aware machine learning framework. Figure contrasting a conventional approach to conducting disparity assessments, which is static, to the analysis we conduct in this paper. Our analysis (1) uses comprehensive health data from over 1,000 primary care practices and 5 million patients across the U.S., (2) timestamped information on the reporting of race to measure delay, and (3) retrospective analyses of disparity assessments under varying levels of delay.
July 24, 2025 at 10:20 AM
allisonkoe.bsky.social
Check out our work at @ic2s2.bsky.social this afternoon during the Communication & Cooperation II session!
emmharv.bsky.social Emma Harvey @emmharv.bsky.social · Jun 23
I am so excited to be in 🇬🇷Athens🇬🇷 to present "A Framework for Auditing Chatbots for Dialect-Based Quality-of-Service Harms" by me, @kizilcec.bsky.social, and @allisonkoe.bsky.social, at #FAccT2025!!

🔗: arxiv.org/pdf/2506.04419
A screenshot of our paper's: Title: A Framework for Auditing Chatbots for Dialect-Based Quality-of-Service Harms Authors: Emma Harvey, Rene Kizilcec, Allison Koenecke Abstract: Increasingly, individuals who engage in online activities are expected to interact with large language model (LLM)-based chatbots. Prior work has shown that LLMs can display dialect bias, which occurs when they produce harmful responses when prompted with text written in minoritized dialects. However, whether and how this bias propagates to systems built on top of LLMs, such as chatbots, is still unclear. We conduct a review of existing approaches for auditing LLMs for dialect bias and show that they cannot be straightforwardly adapted to audit LLM-based chatbots due to issues of substantive and ecological validity. To address this, we present a framework for auditing LLM-based chatbots for dialect bias by measuring the extent to which they produce quality-of-service harms, which occur when systems do not work equally well for different people. Our framework has three key characteristics that make it useful in practice. First, by leveraging dynamically generated instead of pre-existing text, our framework enables testing over any dialect, facilitates multi-turn conversations, and represents how users are likely to interact with chatbots in the real world. Second, by measuring quality-of-service harms, our framework aligns audit results with the real-world outcomes of chatbot use. Third, our framework requires only query access to an LLM-based chatbot, meaning that it can be leveraged equally effectively by internal auditors, external auditors, and even individual users in order to promote accountability. To demonstrate the efficacy of our framework, we conduct a case study audit of Amazon Rufus, a widely-used LLM-based chatbot in the customer service domain. Our results reveal that Rufus produces lower-quality responses to prompts written in minoritized English dialects.
July 23, 2025 at 10:01 AM
allisonkoe.bsky.social
Presenting this work at @ic2s2.bsky.social imminently, in the LLMs & Society session!
July 22, 2025 at 9:15 AM
allisonkoe.bsky.social
For folks at @ic2s2.bsky.social, I'm excited to be sharing this work at this afternoon's session on LLMs & Bias!
allisonkoe.bsky.social Allison Koenecke @allisonkoe.bsky.social · Jun 22
🎉Excited to present our paper tomorrow at @facct.bsky.social, “Characterizing Bias: Benchmarking Large Language Models in Simplified versus Traditional Chinese”, with @brucelyu17.bsky.social, Jiebo Luo and Jian Kang, revealing 🤖 LLM performance disparities. 📄 Link: arxiv.org/abs/2505.22645
"Characterizing Bias: Benchmarking Large Language Models in Simplified versus Traditional Chinese" Abstract: While the capabilities of Large Language Models (LLMs) have been studied in both Simplified and Traditional Chinese, it is yet unclear whether LLMs exhibit differential performance when prompted in these two variants of written Chinese. This understanding is critical, as disparities in the quality of LLM responses can perpetuate representational harms by ignoring the different cultural contexts underlying Simplified versus Traditional Chinese, and can exacerbate downstream harms in LLM-facilitated decision-making in domains such as education or hiring. To investigate potential LLM performance disparities, we design two benchmark tasks that reflect real-world scenarios: regional term choice (prompting the LLM to name a described item which is referred to differently in Mainland China and Taiwan), and regional name choice (prompting the LLM to choose who to hire from a list of names in both Simplified and Traditional Chinese). For both tasks, we audit the performance of 11 leading commercial LLM services and open-sourced models -- spanning those primarily trained on English, Simplified Chinese, or Traditional Chinese. Our analyses indicate that biases in LLM responses are dependent on both the task and prompting language: while most LLMs disproportionately favored Simplified Chinese responses in the regional term choice task, they surprisingly favored Traditional Chinese names in the regional name choice task. We find that these disparities may arise from differences in training data representation, written character preferences, and tokenization of Simplified and Traditional Chinese. These findings highlight the need for further analysis of LLM biases; as such, we provide an open-sourced benchmark dataset to foster reproducible evaluations of future LLM behavior across Chinese language variants (this https URL). Figure showing that three different LLMs (GPT-4o, Qwen-1.5, and Taiwan-LLM) may answer a prompt about pineapples differently when asked in Simplified Chinese vs. Traditional Chinese. Figure showing that LLMs disproportionately answer questions about regional-specific terms (like the word for "pineapple," which differs in Simplified and Traditional Chinese) correctly when prompted in Simplified Chinese as opposed to Traditional Chinese. Figure showing that LLMs have high variance of adhering to prompt instructions, favoring Traditional Chinese names over Simplified Chinese names in a benchmark task regarding hiring.
July 22, 2025 at 7:06 AM
allisonkoe.bsky.social
This Thursday at @facct.bsky.social, @jennahgosciak.bsky.social's presenting our work at the 10:45am "Audits 2" session! We collaborated across @cornellbowers.bsky.social, @mit.edu, & @stanfordlaw.bsky.social to study health estimate biases from delayed race data collection: arxiv.org/abs/2506.13735
June 24, 2025 at 3:40 PM
allisonkoe.bsky.social
For folks at @facct.bsky.social, our very own @cornellbowers.bsky.social student @emmharv.bsky.social will present the Best-Paper-Award-winning work she led on Wednesday at 10:45 AM in the "Audit and Evaluation Approaches" session!

In the meantime, 🧵 below and 🔗 here: arxiv.org/abs/2506.04419 !
June 23, 2025 at 2:49 PM
allisonkoe.bsky.social
🎉Excited to present our paper tomorrow at @facct.bsky.social, “Characterizing Bias: Benchmarking Large Language Models in Simplified versus Traditional Chinese”, with @brucelyu17.bsky.social, Jiebo Luo and Jian Kang, revealing 🤖 LLM performance disparities. 📄 Link: arxiv.org/abs/2505.22645
"Characterizing Bias: Benchmarking Large Language Models in Simplified versus Traditional Chinese" Abstract: While the capabilities of Large Language Models (LLMs) have been studied in both Simplified and Traditional Chinese, it is yet unclear whether LLMs exhibit differential performance when prompted in these two variants of written Chinese. This understanding is critical, as disparities in the quality of LLM responses can perpetuate representational harms by ignoring the different cultural contexts underlying Simplified versus Traditional Chinese, and can exacerbate downstream harms in LLM-facilitated decision-making in domains such as education or hiring. To investigate potential LLM performance disparities, we design two benchmark tasks that reflect real-world scenarios: regional term choice (prompting the LLM to name a described item which is referred to differently in Mainland China and Taiwan), and regional name choice (prompting the LLM to choose who to hire from a list of names in both Simplified and Traditional Chinese). For both tasks, we audit the performance of 11 leading commercial LLM services and open-sourced models -- spanning those primarily trained on English, Simplified Chinese, or Traditional Chinese. Our analyses indicate that biases in LLM responses are dependent on both the task and prompting language: while most LLMs disproportionately favored Simplified Chinese responses in the regional term choice task, they surprisingly favored Traditional Chinese names in the regional name choice task. We find that these disparities may arise from differences in training data representation, written character preferences, and tokenization of Simplified and Traditional Chinese. These findings highlight the need for further analysis of LLM biases; as such, we provide an open-sourced benchmark dataset to foster reproducible evaluations of future LLM behavior across Chinese language variants (this https URL). Figure showing that three different LLMs (GPT-4o, Qwen-1.5, and Taiwan-LLM) may answer a prompt about pineapples differently when asked in Simplified Chinese vs. Traditional Chinese. Figure showing that LLMs disproportionately answer questions about regional-specific terms (like the word for "pineapple," which differs in Simplified and Traditional Chinese) correctly when prompted in Simplified Chinese as opposed to Traditional Chinese. Figure showing that LLMs have high variance of adhering to prompt instructions, favoring Traditional Chinese names over Simplified Chinese names in a benchmark task regarding hiring.
June 22, 2025 at 9:16 PM
Reposted by Allison Koenecke
nkgarg.bsky.social
I wrote about science cuts and my family's immigration story as part of The McClintock Letters organized by @cornellasap.bsky.social. Haven't yet placed it in a Houston-based newspaper but hopefully it's useful here

gargnikhil.com/posts/202506...
Science and immigration cuts · Nikhil Garg
gargnikhil.com
June 16, 2025 at 11:09 AM
Reposted by Allison Koenecke
dynarski.bsky.social
This framing is all wrong

Our international students are not a “crucial funding source”

They are our STUDENTS

They are the reason we EXIST

We teach STUDENTS
By Michael S. Schmidt and Michael C. Bender May 22, 2025 Updated 2:17 p.m. ET The Trump administration on Thursday halted Harvard University's ability to enroll international students, taking aim at a crucial funding source for the nation's oldest and wealthiest college in a major escalation in the administration's efforts to pressure the elite school to fall in line with the president's agenda.
May 22, 2025 at 6:21 PM
allisonkoe.bsky.social
It was a pleasure writing this piece with experts across both data science and public services. We need more in-house technical expertise in government! Read more here: cacm.acm.org/opinion/as-g...
May 3, 2025 at 4:44 AM
Reposted by Allison Koenecke
nkgarg.bsky.social
Really proud of @rajmovva.bsky.social and @kennypeng.bsky.social for this work! We hope that it's useful, and are already using it for many followup projects

Preprint: arxiv.org/abs/2502.04382
Python package: github.com/rmovva/Hypot...
Demo: hypothesaes.org
rajmovva.bsky.social Raj Movva @rajmovva.bsky.social · Mar 18
💡New preprint & Python package: We use sparse autoencoders to generate hypotheses from large text datasets.

Our method, HypotheSAEs, produces interpretable text features that predict a target variable, e.g. features in news headlines that predict engagement. 🧵1/
March 18, 2025 at 3:21 PM
allisonkoe.bsky.social
Excited for
@emmharv.bsky.social
to present her CHI paper next month - thorough and ever-timely research on the harms of LLMs in education! arXiv link here: arxiv.org/pdf/2502.14592
March 13, 2025 at 4:26 PM
Reposted by Allison Koenecke
sjgreenwood.bsky.social
Please repost to get the word out! @nkgarg.bsky.social and I are excited to present a personalized feed for academics! It shows posts about papers from accounts you’re following bsky.app/profile/pape...
March 10, 2025 at 3:12 PM
Reposted by Allison Koenecke
nkgarg.bsky.social
Now online @pnasnexus.org! Many discrimination auditing and electoral tasks use ML to predict race/ethnicity – by discretizing continuous scores. Can the discretization process cause bias in labels and downstream tasks? Yes! Led by @evandyx.bsky.social

academic.oup.com/pnasnexus/ar...
Paper screenshot. Title: Addressing discretization-induced bias in demographic prediction Abstract: Racial and other demographic imputation is necessary for many applications, especially in auditing disparities and outreach targeting in political campaigns. The canonical approach is to construct continuous predictions—e.g. based on name and geography—and then to often discretize the predictions by selecting the most likely class (argmax), potentially with a minimum threshold (thresholding). We study how this practice produces discretization bias. For example, we show that argmax labeling, as used by a prominent commercial voter file vendor to impute race/ethnicity, results in a substantial under-count of Black voters, e.g. by 28.2% points in North Carolina. This bias can have substantial implications in downstream tasks that use such labels. We then introduce a joint optimization approach—and a tractable data-driven threshold heuristic—that can eliminate this bias, with negligible individual-level accuracy loss. Finally, we theoretically analyze discretization bias, show that calibrated continuous models are insufficient to eliminate it, and that an approach such as ours is necessary. Broadly, we warn researchers and practitioners against discretizing continuous demographic predictions without considering downstream consequences.
February 27, 2025 at 7:43 PM