arXiv subjects

Adam Tauman Kalai

Publications and source records attributed to Adam Tauman Kalai.

At least 19 recordsLinked to original sources

arXiv2025

Consensus Sampling for Safer Generative AI

Motivated by undetectable risks in generative AI, we study a general robust aggregation problem: how to aggregate several probability distributions to boost safety. We present consensus sampling, a black-box algorithm that, given k distributions, has risk competitive with the average risk of the safest $s$ while abstaining when there is insufficient agreement. This yields an architecture-agnostic approach to generative-model safety when the distributions are induced by models that can sample and evaluate output probabilities. We formalize the guarantee through R-robustness, which also bounds information leakage and adversarial influence. Inspired by robust statistics and the provable copyright protection algorithm of Vyas et al (2023), we show that while a standard mixture is vulnerable to one unsafe constituent, a pointwise-median construction provides robust intuition, and our efficient sampler is Pareto-optimal for the tradeoff between worst-case risk and abstention. Experiments on synthetic distributions and image generation illustrate the general mechanism and its motivating safety application. The method requires overlap among safe distributions, but it provides a model-agnostic way to inherit guarantees from an unknown reliable subset.

cs.AI↗

arXiv2025

On Non-interactive Evaluation of Animal Communication Translators

If you had an AI Whale-to-English translator, how could you validate whether or not it is working? Does one need to interact with the animals or rely on grounded observations such as temperature? We provide theoretical and proof-of-concept experimental evidence suggesting that interaction and even observations may not be necessary for sufficiently complex languages. One may be able to evaluate translators solely by their English outputs, offering potential advantages in terms of safety, ethics, and cost. This is an instance of machine translation quality evaluation (MTQE) without any reference translations available. A key challenge is identifying ``hallucinations,'' false translations which may appear fluent and plausible. We propose using segment-by-segment translation together with the classic NLP shuffle test to evaluate translators. The idea is to translate animal communication, turn by turn, and evaluate how often the resulting translations make more sense in order than permuted. Proof-of-concept experiments on data-scarce human languages and constructed languages demonstrate the potential utility of this evaluation methodology. These human-language experiments serve solely to validate our reference-free metric under data scarcity. It is found to correlate highly with a standard evaluation based on reference translations, which are available in our experiments. We also perform a theoretical analysis suggesting that interaction may not be necessary nor efficient in the early stages of learning to translate.

cs.CL↗

arXiv2025

Why Language Models Hallucinate

Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty. Such "hallucinations" persist even in state-of-the-art systems and undermine trust. We argue that language models hallucinate because the training and evaluation procedures reward guessing over acknowledging uncertainty, and we analyze the statistical causes of hallucinations in the modern training pipeline. Hallucinations need not be mysterious -- they originate simply as errors in binary classification. If incorrect statements cannot be distinguished from facts, then hallucinations in pretrained language models will arise through natural statistical pressures. We then argue that hallucinations persist due to the way most evaluations are graded -- language models are optimized to be good test-takers, and guessing when uncertain improves test performance. This "epidemic" of penalizing uncertain responses can only be addressed through a socio-technical mitigation: modifying the scoring of existing benchmarks that are misaligned but dominate leaderboards, rather than introducing additional hallucination evaluations. This change may steer the field toward more trustworthy AI systems.

cs.CL↗

arXiv2025

The Singapore Consensus on Global AI Safety Research Priorities

Rapidly improving AI capabilities and autonomy hold significant promise of transformation, but are also driving vigorous debate on how to ensure that AI is safe, i.e., trustworthy, reliable, and secure. Building a trusted ecosystem is therefore essential -- it helps people embrace AI with confidence and gives maximal space for innovation while avoiding backlash. The "2025 Singapore Conference on AI (SCAI): International Scientific Exchange on AI Safety" aimed to support research in this space by bringing together AI scientists across geographies to identify and synthesise research priorities in AI safety. This resulting report builds on the International AI Safety Report chaired by Yoshua Bengio and backed by 33 governments. By adopting a defence-in-depth model, this report organises AI safety research domains into three types: challenges with creating trustworthy AI systems (Development), challenges with evaluating their risks (Assessment), and challenges with monitoring and intervening after deployment (Control).

cs.AI↗

arXiv2024

First-Person Fairness in Chatbots

Evaluating chatbot fairness is crucial given their rapid proliferation, yet typical chatbot tasks (e.g., resume writing, entertainment) diverge from the institutional decision-making tasks (e.g., resume screening) which have traditionally been central to discussion of algorithmic fairness. The open-ended nature and diverse use-cases of chatbots necessitate novel methods for bias assessment. This paper addresses these challenges by introducing a scalable counterfactual approach to evaluate "first-person fairness," meaning fairness toward chatbot users based on demographic characteristics. Our method employs a Language Model as a Research Assistant (LMRA) to yield quantitative measures of harmful stereotypes and qualitative analyses of demographic differences in chatbot responses. We apply this approach to assess biases in six of our language models across millions of interactions, covering sixty-six tasks in nine domains and spanning two genders and four races. Independent human annotations corroborate the LMRA-generated bias evaluations. This study represents the first large-scale fairness evaluation based on real-world chat data. We highlight that post-training reinforcement learning techniques significantly mitigate these biases. This evaluation provides a practical methodology for ongoing bias monitoring and mitigation.

cs.CY↗

arXiv2024

Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding

We introduce meta-prompting, an effective scaffolding technique designed to enhance the functionality of language models (LMs). This approach transforms a single LM into a multi-faceted conductor, adept at managing and integrating multiple independent LM queries. By employing high-level instructions, meta-prompting guides the LM to break down complex tasks into smaller, more manageable subtasks. These subtasks are then handled by distinct "expert" instances of the same LM, each operating under specific, tailored instructions. Central to this process is the LM itself, in its role as the conductor, which ensures seamless communication and effective integration of the outputs from these expert models. It additionally employs its inherent critical thinking and robust verification processes to refine and authenticate the end result. This collaborative prompting approach empowers a single LM to simultaneously act as a comprehensive orchestrator and a panel of diverse experts, significantly enhancing its performance across a wide array of tasks. The zero-shot, task-agnostic nature of meta-prompting greatly simplifies user interaction by obviating the need for detailed, task-specific instructions. Furthermore, our research demonstrates the seamless integration of external tools, such as a Python interpreter, into the meta-prompting framework, thereby broadening its applicability and utility. Through rigorous experimentation with GPT-4, we establish the superiority of meta-prompting over conventional scaffolding methods: When averaged across all tasks, including the Game of 24, Checkmate-in-One, and Python Programming Puzzles, meta-prompting, augmented with a Python interpreter functionality, surpasses standard prompting by 17.1%, expert (dynamic) prompting by 17.3%, and multipersona prompting by 15.2%.

cs.CL↗

arXiv2023

Calibrated Language Models Must Hallucinate

Recent language models generate false but plausible-sounding text with surprising frequency. Such "hallucinations" are an obstacle to the usability of language-based AI systems and can harm people who rely upon their outputs. This work shows that there is an inherent statistical lower-bound on the rate that pretrained language models hallucinate certain types of facts, having nothing to do with the transformer LM architecture or data quality. For "arbitrary" facts whose veracity cannot be determined from the training data, we show that hallucinations must occur at a certain rate for language models that satisfy a statistical calibration condition appropriate for generative language models. Specifically, if the maximum probability of any fact is bounded, we show that the probability of generating a hallucination is close to the fraction of facts that occur exactly once in the training data (a "Good-Turing" estimate), even assuming ideal training data without errors. One conclusion is that models pretrained to be sufficiently good predictors (i.e., calibrated) may require post-training to mitigate hallucinations on the type of arbitrary facts that tend to appear once in the training set. However, our analysis also suggests that there is no statistical reason that pretraining will lead to hallucination on facts that tend to appear more than once in the training data (like references to publications such as articles and books, whose hallucinations have been particularly notable and problematic) or on systematic facts (like arithmetic calculations). Therefore, different architectures and learning algorithms may mitigate these latter types of hallucinations.

cs.CL↗

arXiv2023

Testing Language Model Agents Safely in the Wild

A prerequisite for safe autonomy-in-the-wild is safe testing-in-the-wild. Yet real-world autonomous tests face several unique safety challenges, both due to the possibility of causing harm during a test, as well as the risk of encountering new unsafe agent behavior through interactions with real-world and potentially malicious actors. We propose a framework for conducting safe autonomous agent tests on the open internet: agent actions are audited by a context-sensitive monitor that enforces a stringent safety boundary to stop an unsafe test, with suspect behavior ranked and logged to be examined by humans. We design a basic safety monitor (AgentMonitor) that is flexible enough to monitor existing LLM agents, and, using an adversarial simulated agent, we measure its ability to identify and stop unsafe situations. Then we apply the AgentMonitor on a battery of real-world tests of AutoGPT, and we identify several limitations and challenges that will face the creation of safe in-the-wild tests as autonomous agents grow more capable.

cs.AI↗

arXiv2023

Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation

Several recent advances in AI systems solve problems by providing a "scaffolding" program that structures multiple calls to language models (LMs) to generate better outputs. A scaffolding program is written in a programming language such as Python. In this work, we use a language-model-infused scaffolding program to improve itself. We start with a seed "improver" that improves an input program according to a given utility function by querying an LM several times and returning the best solution. We then run this seed improver to improve itself. Across a small set of downstream tasks, the resulting improved improver generates programs with significantly better performance than its seed improver. A variety of self-improvement strategies are proposed by the language model, including beam search, genetic algorithms, and simulated annealing. Since the language models themselves are not altered, this is not full recursive self-improvement. Nonetheless, it demonstrates that a modern language model, GPT-4 in our experiments, is capable of writing code that can call itself to improve itself. We consider concerns around the development of self-improving technologies and evaluate the frequency with which the generated code bypasses a sandbox.

cs.CL↗

arXiv2023

Textbooks Are All You Need

We introduce phi-1, a new large language model for code, with significantly smaller size than competing models: phi-1 is a Transformer-based model with 1.3B parameters, trained for 4 days on 8 A100s, using a selection of ``textbook quality" data from the web (6B tokens) and synthetically generated textbooks and exercises with GPT-3.5 (1B tokens). Despite this small scale, phi-1 attains pass@1 accuracy 50.6% on HumanEval and 55.5% on MBPP. It also displays surprising emergent properties compared to phi-1-base, our model before our finetuning stage on a dataset of coding exercises, and phi-1-small, a smaller model with 350M parameters trained with the same pipeline as phi-1 that still achieves 45% on HumanEval.

cs.CL↗

arXiv2023

Do Language Models Know When They're Hallucinating References?

State-of-the-art language models (LMs) are notoriously susceptible to generating hallucinated information. Such inaccurate outputs not only undermine the reliability of these models but also limit their use and raise serious concerns about misinformation and propaganda. In this work, we focus on hallucinated book and article references and present them as the "model organism" of language model hallucination research, due to their frequent and easy-to-discern nature. We posit that if a language model cites a particular reference in its output, then it should ideally possess sufficient information about its authors and content, among other relevant details. Using this basic insight, we illustrate that one can identify hallucinated references without ever consulting any external resources, by asking a set of direct or indirect queries to the language model about the references. These queries can be considered as "consistency checks." Our findings highlight that while LMs, including GPT-4, often produce inconsistent author lists for hallucinated references, they also often accurately recall the authors of real references. In this sense, the LM can be said to "know" when it is hallucinating references. Furthermore, these findings show how hallucinated references can be dissected to shed light on their nature. Replication code and results can be found at https://github.com/microsoft/hallucinated-references.

cs.CL↗

arXiv2023

Loss Minimization Yields Multicalibration for Large Neural Networks

Multicalibration is a notion of fairness for predictors that requires them to provide calibrated predictions across a large set of protected groups. Multicalibration is known to be a distinct goal than loss minimization, even for simple predictors such as linear functions. In this work, we consider the setting where the protected groups can be represented by neural networks of size $k$, and the predictors are neural networks of size $n > k$. We show that minimizing the squared loss over all neural nets of size $n$ implies multicalibration for all but a bounded number of unlucky values of $n$. We also give evidence that our bound on the number of unlucky values is tight, given our proof technique. Previously, results of the flavor that loss minimization yields multicalibration were known only for predictors that were near the ground truth, hence were rather limited in applicability. Unlike these, our results rely on the expressivity of neural nets and utilize the representation of the predictor.

cs.LG↗

arXiv2022

A Theory of Unsupervised Translation Motivated by Understanding Animal Communication

Neural networks are capable of translating between languages -- in some cases even between two languages where there is little or no access to parallel translations, in what is known as Unsupervised Machine Translation (UMT). Given this progress, it is intriguing to ask whether machine learning tools can ultimately enable understanding animal communication, particularly that of highly intelligent animals. We propose a theoretical framework for analyzing UMT when no parallel translations are available and when it cannot be assumed that the source and target corpora address related subject domains or posses similar linguistic structure. We exemplify this theory with two stylized models of language, for which our framework provides bounds on necessary sample complexity; the bounds are formally proven and experimentally verified on synthetic data. These bounds show that the error rates are inversely related to the language complexity and amount of common ground. This suggests that unsupervised translation of animal communication may be feasible if the communication system is sufficiently complex.

cs.CL↗

arXiv2022

Recurrent Convolutional Neural Networks Learn Succinct Learning Algorithms

Neural networks (NNs) struggle to efficiently solve certain problems, such as learning parities, even when there are simple learning algorithms for those problems. Can NNs discover learning algorithms on their own? We exhibit a NN architecture that, in polynomial time, learns as well as any efficient learning algorithm describable by a constant-sized program. For example, on parity problems, the NN learns as well as Gaussian elimination, an efficient algorithm that can be succinctly described. Our architecture combines both recurrent weight sharing between layers and convolutional weight sharing to reduce the number of parameters down to a constant, even though the network itself may have trillions of nodes. While in practice the constants in our analysis are too large to be directly meaningful, our work suggests that the synergy of Recurrent and Convolutional NNs (RCNNs) may be more natural and powerful than either alone, particularly for concisely parameterizing discrete algorithms.

cs.LG↗

arXiv2022

Partial Matrix Completion

The matrix completion problem aims to reconstruct a low-rank matrix based on a revealed set of possibly noisy entries. Prior works consider completing the entire matrix with generalization error guarantees. However, the completion accuracy can be drastically different over different entries. This work establishes a new framework of partial matrix completion, where the goal is to identify a large subset of the entries that can be completed with high confidence. We propose an efficient algorithm with the following provable guarantees. Given access to samples from an unknown and arbitrary distribution, it guarantees: (a) high accuracy over completed entries, and (b) high coverage of the underlying distribution. We also consider an online learning variant of this problem, where we propose a low-regret algorithm based on iterative gradient updates. Preliminary empirical evaluations are included.

cs.LG↗

arXiv2022

Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies

We introduce a new type of test, called a Turing Experiment (TE), for evaluating to what extent a given language model, such as GPT models, can simulate different aspects of human behavior. A TE can also reveal consistent distortions in a language model's simulation of a specific human behavior. Unlike the Turing Test, which involves simulating a single arbitrary individual, a TE requires simulating a representative sample of participants in human subject research. We carry out TEs that attempt to replicate well-established findings from prior studies. We design a methodology for simulating TEs and illustrate its use to compare how well different language models are able to reproduce classic economic, psycholinguistic, and social psychology experiments: Ultimatum Game, Garden Path Sentences, Milgram Shock Experiment, and Wisdom of Crowds. In the first three TEs, the existing findings were replicated using recent models, while the last TE reveals a "hyper-accuracy distortion" present in some language models (including ChatGPT and GPT-4), which could affect downstream applications in education and the arts.

cs.CL↗

arXiv2022

Language Models Can Teach Themselves to Program Better

Recent Language Models (LMs) achieve breakthrough performance in code generation when trained on human-authored problems, even solving some competitive-programming problems. Self-play has proven useful in games such as Go, and thus it is natural to ask whether LMs can generate their own instructive programming problems to improve their performance. We show that it is possible for an LM to synthesize programming problems and solutions, which are filtered for correctness by a Python interpreter. The LM's performance is then seen to improve when it is fine-tuned on its own synthetic problems and verified solutions; thus the model 'improves itself' using the Python interpreter. Problems are specified formally as programming puzzles [Schuster et al., 2021], a code-based problem format where solutions can easily be verified for correctness by execution. In experiments on publicly-available LMs, test accuracy more than doubles. This work demonstrates the potential for code LMs, with an interpreter, to generate instructive problems and improve their own performance.

cs.LG↗

arXiv2022

Why GANs are overkill for NLP

This work offers a novel theoretical perspective on why, despite numerous attempts, adversarial approaches to generative modeling (e.g., GANs) have not been as popular for certain generation tasks, particularly sequential tasks such as Natural Language Generation, as they have in others, such as Computer Vision. In particular, on sequential data such as text, maximum-likelihood approaches are significantly more utilized than GANs. We show that, while it may seem that maximizing likelihood is inherently different than minimizing distinguishability, this distinction is largely artificial and only holds for limited models. We argue that minimizing KL-divergence (i.e., maximizing likelihood) is a more efficient approach to effectively minimizing the same distinguishability criteria that adversarial models seek to optimize. Reductions show that minimizing distinguishability can be seen as simply boosting likelihood for certain families of models including n-gram models and neural networks with a softmax output layer. To achieve a full polynomial-time reduction, a novel next-token distinguishability model is considered.

cs.LG↗