Author name cluster

Emre Kiciman

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.

8 papers

2 author rows

ICML Conference 2025 Conference Paper

RLTHF: Targeted Human Feedback for LLM Alignment

Yifei Xu
Tusher Chakraborty
Emre Kiciman
Bibek Aryal
Srinagesh Sharma
Songwu Lu
Ranveer Chandra

Fine-tuning large language models (LLMs) to align with user preferences is challenging due to the high cost of quality human annotations in Reinforcement Learning from Human Feedback (RLHF) and the generalizability limitations of AI Feedback. To address these challenges, we propose RLTHF, a human-AI hybrid framework that combines LLM-based initial alignment with selective human annotations to achieve full-human annotation alignment with minimal effort. RLTHF identifies hard-to-annotate samples mislabeled by LLMs using a reward model’s reward distribution and iteratively enhances alignment by integrating strategic human corrections while leveraging LLM’s correctly labeled samples. Evaluations on HH-RLHF and TL; DR datasets show that RLTHF reaches full-human annotation-level alignment with only 6-7% of the human annotation effort. Furthermore, models trained on RLTHF’s curated datasets for downstream tasks outperform those trained on fully human-annotated datasets, underscoring the effectiveness of RLTHF.

Details

ICLR Conference 2025 Conference Paper

Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations

Katie Matton
Robert Osazuwa Ness
John V. Guttag
Emre Kiciman

Large language models (LLMs) are capable of generating *plausible* explanations of how they arrived at an answer to a question. However, these explanations can misrepresent the model's "reasoning" process, i.e., they can be *unfaithful*. This, in turn, can lead to over-trust and misuse. We introduce a new approach for measuring the faithfulness of LLM explanations. First, we provide a rigorous definition of faithfulness. Since LLM explanations mimic human explanations, they often reference high-level *concepts* in the input question that purportedly influenced the model. We define faithfulness in terms of the difference between the set of concepts that the LLM's *explanations imply* are influential and the set that *truly* are. Second, we present a novel method for estimating faithfulness that is based on: (1) using an auxiliary LLM to modify the values of concepts within model inputs to create realistic counterfactuals, and (2) using a hierarchical Bayesian model to quantify the causal effects of concepts at both the example- and dataset-level. Our experiments show that our method can be used to quantify and discover interpretable patterns of unfaithfulness. On a social bias task, we uncover cases where LLM explanations hide the influence of social bias. On a medical question answering task, we uncover cases where LLM explanations provide misleading claims about which pieces of evidence influenced the model's decisions.

Details

TMLR Journal 2024 Journal Article

Causal Reasoning and Large Language Models: Opening a New Frontier for Causality

Emre Kiciman
Robert Ness
Amit Sharma
Chenhao Tan

The causal capabilities of large language models (LLMs) are a matter of significant debate, with critical implications for the use of LLMs in societally impactful domains such as medicine, science, law, and policy. We conduct a "behavorial" study of LLMs to benchmark their capability in generating causal arguments. Across a wide range of tasks, we find that LLMs can generate text corresponding to correct causal arguments with high probability, surpassing the best-performing existing methods. Algorithms based on GPT-3.5 and 4 outperform existing algorithms on a pairwise causal discovery task (97%, 13 points gain), counterfactual reasoning task (92%, 20 points gain) and event causality (86% accuracy in determining necessary and sufficient causes in vignettes). We perform robustness checks across tasks and show that the capabilities cannot be explained by dataset memorization alone, especially since LLMs generalize to novel datasets that were created after the training cutoff date. That said, LLMs exhibit unpredictable failure modes and we discuss the kinds of errors that may be improved and what are the fundamental limits of LLM-based answers. Overall, by operating on the text metadata, LLMs bring capabilities so far understood to be restricted to humans, such as using collected knowledge to generate causal graphs or identifying background causal context from natural language. As a result, LLMs may be used by human domain experts to save effort in setting up a causal analysis, one of the biggest impediments to the widespread adoption of causal methods. Given that LLMs ignore the actual data, our results also point to a fruitful research direction of developing algorithms that combine LLMs with existing causal techniques. Code and datasets are available at https://github.com/py-why/pywhy-llm.

PDF Details

TMLR Journal 2024 Journal Article

Deep End-to-end Causal Inference

Tomas Geffner
Javier Antoran
Adam Foster
Wenbo Gong
Chao Ma
Emre Kiciman
Amit Sharma
Angus Lamb

Causal inference is essential for data-driven decision-making across domains such as business engagement, medical treatment, and policy making. However, in practice, causal inference suffers from many limitations including unknown causal graphs, missing data problems, and mixed data types. To tackle those challenges, we develop Deep End-to-end Causal Inference (DECI) framework, a flow based non-linear additive noise model combined with variational inference, which can perform both Bayesian causal discovery and inference. Theoretically, we show that DECI unifies many existing structural equation model (SEM) based causal inference techniques and can recover the ground truth mechanism under standard assumptions. Motivated by the challenges in the real world, we further extend DECI to heterogeneous, mixed-type data with missing values, allowing for both continuous and discrete treatment decisions. Empirically, we conduct extensive experiments (over a thousand) to show the competitive performance of DECI when compared to relevant baselines for both causal discovery and inference with both synthetic and causal machine learning benchmarks across data types and levels of missingness.

PDF Details

ICLR Conference 2023 Conference Paper

Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization

Jivat Neet Kaur
Emre Kiciman
Amit Sharma 0007

Recent empirical studies on domain generalization (DG) have shown that DG algorithms that perform well on some distribution shifts fail on others, and no state-of-the-art DG algorithm performs consistently well on all shifts. Moreover, real-world data often has multiple distribution shifts over different attributes; hence we introduce multi-attribute distribution shift datasets and find that the accuracy of existing DG algorithms falls even further. To explain these results, we provide a formal characterization of generalization under multi-attribute shifts using a canonical causal graph. 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. As a result, we prove that any algorithm based on a single, fixed constraint cannot work well across all shifts, providing theoretical evidence for mixed empirical results on DG algorithms. Based on this insight, we develop Causally Adaptive Constraint Minimization (CACM), an algorithm that uses knowledge about the data-generating process to adaptively identify and apply the correct independence constraints for regularization. Results on fully synthetic, MNIST, small NORB, and Waterbirds datasets, covering binary and multi-valued attributes and labels, show that adaptive dataset-dependent constraints lead to the highest accuracy on unseen domains whereas incorrect constraints fail to do so. Our results demonstrate the importance of modeling the causal relationships inherent in the data-generating process.

Details

AAAI Conference 2022 Conference Paper

Investigations of Performance and Bias in Human-AI Teamwork in Hiring

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. While prior work studies the effects of model accuracy on humans, we endeavour here to investigate the complex dynamics of how both a model’s predictive performance and bias may transfer to humans in a recommendation-aided decision task. We consider the domain of ML-assisted hiring, where humans—operating in a constrained selection setting—can choose whether they wish to utilize a trained model’s inferences to help select candidates from written biographies. We conduct a large-scale user study leveraging a re-created dataset of real bios from prior work, where humans predict the ground truth occupation of given candidates with and without the help of three different NLP classifiers (random, bag-of-words, and deep neural network). Our results demonstrate that while high-performance models significantly improve human performance in a hybrid setting, some models mitigate hybrid bias while others accentuate it. We examine these findings through the lens of decision conformity and observe that our model architecture choices have an impact on human-AI conformity and bias, motivating the explicit need to assess these complex dynamics prior to deployment.

PDF Details

NeurIPS Conference 2020 Conference Paper

AvE: Assistance via Empowerment

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). Existing methods tend to rely on inferring the human's goal, which is challenging when there are many potential goals or when the set of candidate goals is difficult to identify. We propose a new paradigm for assistance by instead increasing the human's ability to control their environment, and formalize this approach by augmenting reinforcement learning with human empowerment. This task-agnostic objective increases the person's autonomy and ability to achieve any eventual state. We test our approach against assistance based on goal inference, highlighting scenarios where our method overcomes failure modes stemming from goal ambiguity or misspecification. As existing methods for estimating empowerment in continuous domains are computationally hard, precluding its use in real time learned assistance, we also propose an efficient empowerment-inspired proxy metric. Using this, we are able to successfully demonstrate our method in a shared autonomy user study for a challenging simulated teleoperation task with human-in-the-loop training.

PDF Details

NeurIPS Conference 2007 Conference Paper

Fast Variational Inference for Large-scale Internet Diagnosis

Emre Kiciman
David Maltz
John Platt

Web servers on the Internet need to maintain high reliability, but the cause of intermittent failures of web transactions is non-obvious. We use Bayesian inference to diagnose problems with web services. This diagnosis problem is far larger than any previously attempted: it requires inference of 10^4 possible faults from 10^5 observations. Further, such inference must be performed in less than a second. Inference can be done at this speed by combining a variational approximation, a mean-field approximation, and the use of stochastic gradient descent to optimize a variational cost function. We use this fast inference to diagnose a time series of anomalous HTTP requests taken from a real web service. The inference is fast enough to analyze network logs with billions of entries in a matter of hours.

PDF Details