no code implementations • 20 Mar 2024 • Keegan Hines, Gary Lopez, Matthew Hall, Federico Zarfati, Yonatan Zunger, Emre Kiciman
Indirect prompt injection attacks take advantage of this vulnerability by embedding adversarial instructions into untrusted data being processed alongside user commands.
no code implementations • 13 Jan 2024 • Somya Sharma, Swati Sharma, Rafael Padilha, Emre Kiciman, Ranveer Chandra
Using the sensor data, we preserve underlying causal relations among sensor attributes and organic matter.
1 code implementation • 21 Dec 2023 • Jingwei Yi, Yueqi Xie, Bin Zhu, Emre Kiciman, Guangzhong Sun, Xing Xie, Fangzhao Wu
Based on the evaluation, our work makes a key analysis of the underlying reason for the success of the attack, namely the inability of LLMs to distinguish between instructions and external content and the absence of LLMs' awareness to not execute instructions within external content.
no code implementations • 11 Dec 2023 • Sara Abdali, Anjali Parikh, Steve Lim, Emre Kiciman
Microsoft Windows Feedback Hub is designed to receive customer feedback on a wide variety of subjects including critical topics such as power and battery.
1 code implementation • 4 Dec 2023 • Giovanni Monea, Maxime Peyrard, Martin Josifoski, Vishrav Chaudhary, Jason Eisner, Emre Kiciman, Hamid Palangi, Barun Patra, Robert West
Yet the mechanisms underlying this contextual grounding remain unknown, especially in situations where contextual information contradicts factual knowledge stored in the parameters, which LLMs also excel at recalling.
no code implementations • 2 Nov 2023 • Javier González, Cliff Wong, Zelalem Gero, Jass Bagga, Risa Ueno, Isabel Chien, Eduard Oravkin, Emre Kiciman, Aditya Nori, Roshanthi Weerasinghe, Rom S. Leidner, Brian Piening, Tristan Naumann, Carlo Bifulco, Hoifung Poon
The rapid digitization of real-world data offers an unprecedented opportunity for optimizing healthcare delivery and accelerating biomedical discovery.
no code implementations • 15 Jun 2023 • Somya Sharma, Swati Sharma, Licheng Liu, Rishabh Tushir, Andy Neal, Robert Ness, John Crawford, Emre Kiciman, Ranveer Chandra
Process-based models and analyzing observed data provide two avenues for improving our understanding of soil processes.
no code implementations • 28 Apr 2023 • Emre Kiciman, Robert Ness, Amit Sharma, Chenhao Tan
The causal capabilities of large language models (LLMs) is a matter of significant debate, with critical implications for the use of LLMs in societally impactful domains such as medicine, science, law, and policy.
no code implementations • 22 Jan 2023 • Arash Nasr-Esfahany, Emre Kiciman
The size of this error can be an essential metric for deciding whether or not DSCMs are a viable approach for counterfactual inference in a specific problem setting.
no code implementations • 10 Nov 2022 • Somya Sharma, Swati Sharma, Andy Neal, Sara Malvar, Eduardo Rodrigues, John Crawford, Emre Kiciman, Ranveer Chandra
Measuring and monitoring soil organic carbon is critical for agricultural productivity and for addressing critical environmental problems.
1 code implementation • 13 Oct 2022 • Martin Josifoski, Maxime Peyrard, Frano Rajic, Jiheng Wei, Debjit Paul, Valentin Hartmann, Barun Patra, Vishrav Chaudhary, Emre Kiciman, Boi Faltings, Robert West
Specifically, by analyzing the correlation between the likelihood and the utility of predictions across a diverse set of tasks, we provide empirical evidence supporting the proposed taxonomy and a set of principles to structure reasoning when choosing a decoding algorithm.
no code implementations • 7 Oct 2022 • Parikshit Bansal, Yashoteja Prabhu, Emre Kiciman, Amit Sharma
To explain this generalization failure, we consider an intervention-based importance metric, which shows that a fine-tuned model captures spurious correlations and fails to learn the causal features that determine the relevance between any two text inputs.
no code implementations • 15 Jun 2022 • Jivat Neet Kaur, Emre Kiciman, Amit Sharma
Based on the relationship between spurious attributes and the classification label, we obtain realizations of the canonical causal graph that characterize common distribution shifts and show that each shift entails different independence constraints over observed variables.
no code implementations • 21 Feb 2022 • Andi Peng, Besmira Nushi, Emre Kiciman, Kori Inkpen, Ece Kamar
In AI-assisted decision-making, effective hybrid (human-AI) teamwork is not solely dependent on AI performance alone, but also on its impact on human decision-making.
1 code implementation • 4 Feb 2022 • Tomas Geffner, Javier Antoran, Adam Foster, Wenbo Gong, Chao Ma, Emre Kiciman, Amit Sharma, Angus Lamb, Martin Kukla, Nick Pawlowski, Miltiadis Allamanis, Cheng Zhang
Causal inference is essential for data-driven decision making across domains such as business engagement, medical treatment and policy making.
1 code implementation • 16 Oct 2021 • Maxime Peyrard, Sarvjeet Singh Ghotra, Martin Josifoski, Vidhan Agarwal, Barun Patra, Dean Carignan, Emre Kiciman, Robert West
In particular, we adapt a game-theoretic formulation of IRM (IRM-games) to language models, where the invariance emerges from a specific training schedule in which all the environments compete to optimize their own environment-specific loss by updating subsets of the model in a round-robin fashion.
no code implementations • 29 Sep 2021 • Tomas Geffner, Emre Kiciman, Angus Lamb, Martin Kukla, Miltiadis Allamanis, Cheng Zhang
Current causal discovery methods either fail to scale, model only limited forms of functional relationships, or cannot handle missing values.
1 code implementation • 27 Aug 2021 • Amit Sharma, Vasilis Syrgkanis, Cheng Zhang, Emre Kiciman
Estimation of causal effects involves crucial assumptions about the data-generating process, such as directionality of effect, presence of instrumental variables or mediators, and whether all relevant confounders are observed.
no code implementations • 17 Feb 2021 • Kristina Gligorić, Ryen W. White, Emre Kiciman, Eric Horvitz, Arnaud Chiolero, Robert West
To estimate causal effects from the passively observed log data, we control confounds in a matched quasi-experimental design: we identify focal users who at first do not have any regular eating partners but then start eating with a fixed partner regularly, and we match focal users into comparison pairs such that paired users are nearly identical with respect to covariates measured before acquiring the partner, where the two focal users' new eating partners diverge in the healthiness of their respective food choice.
no code implementations • 16 Jan 2021 • Ruocheng Guo, Pengchuan Zhang, Hao liu, Emre Kiciman
Nevertheless, we find that the performance of IRM can be dramatically degraded under \emph{strong $\Lambda$ spuriousness} -- when the spurious correlation between the spurious features and the class label is strong due to the strong causal influence of their common cause, the domain label, on both of them (see Fig.
no code implementations • 11 Nov 2020 • Yanbo Xu, Divyat Mahajan, Liz Manrao, Amit Sharma, Emre Kiciman
For many kinds of interventions, such as a new advertisement, marketing intervention, or feature recommendation, it is important to target a specific subset of people for maximizing its benefits at minimum cost or potential harm.
4 code implementations • 9 Nov 2020 • Amit Sharma, Emre Kiciman
In addition to efficient statistical estimators of a treatment's effect, successful application of causal inference requires specifying assumptions about the mechanisms underlying observed data and testing whether they are valid, and to what extent.
no code implementations • 17 Oct 2020 • Shuxi Zeng, Murat Ali Bayir, Joesph J. Pfeiffer III, Denis Charles, Emre Kiciman
We describe a causal transfer random forest (CTRF) that combines existing training data with a small amount of data from a randomized experiment to train a model which is robust to the feature shifts and therefore transfers to a new targeting distribution.
no code implementations • 15 Oct 2020 • Razieh Nabi, Joel Pfeiffer, Murat Ali Bayir, Denis Charles, Emre Kiciman
This assumption is violated in settings where units are related through a network of dependencies.
no code implementations • 13 Jul 2020 • Ivan Evtimov, Weidong Cui, Ece Kamar, Emre Kiciman, Tadayoshi Kohno, Jerry Li
Machine learning (ML) models deployed in many safety- and business-critical systems are vulnerable to exploitation through adversarial examples.
1 code implementation • NeurIPS 2020 • Yuqing Du, Stas Tiomkin, Emre Kiciman, Daniel Polani, Pieter Abbeel, Anca Dragan
One difficulty in using artificial agents for human-assistive applications lies in the challenge of accurately assisting with a person's goal(s).
no code implementations • 22 May 2020 • Yuhang Song, Wenbo Li, Lei Zhang, Jianwei Yang, Emre Kiciman, Hamid Palangi, Jianfeng Gao, C. -C. Jay Kuo, Pengchuan Zhang
We study in this paper the problem of novel human-object interaction (HOI) detection, aiming at improving the generalization ability of the model to unseen scenarios.
no code implementations • 8 Sep 2019 • Andi Peng, Besmira Nushi, Emre Kiciman, Kori Inkpen, Siddharth Suri, Ece Kamar
Although systematic biases in decision-making are widely documented, the ways in which they emerge from different sources is less understood.
no code implementations • NeurIPS 2007 • Emre Kiciman, David Maltz, John C. Platt
Web servers on the Internet need to maintain high reliability, but the cause of intermittent failures of web transactions is non-obvious.