Dylan Bouchard

Dylan Bouchard

Bias and fairness risks in Large Language Models (LLMs) vary substantially across deployment contexts, yet existing approaches lack systematic guidance for selecting appropriate evaluation metrics. We present a decision framework that maps LLM use cases, characterized by a model and population of prompts, to relevant bias and fairness metrics based on task type, whether prompts contain protected attribute mentions, and stakeholder priorities. Our framework addresses toxicity, stereotyping, counterfactual unfairness, and allocational harms, and introduces novel metrics based on stereotype classifiers and counterfactual adaptations of text similarity measures. All metrics require only LLM outputs for computation, simplifying implementation while avoiding embedding-based approaches that often correlate poorly with downstream harms. We provide an open-source Python library, LangFair, for practical adoption. Extensive experiments demonstrate that fairness risks cannot be reliably assessed from benchmark performance alone: results on one prompt dataset likely overstate or understate risks for another, underscoring that fairness evaluation must be grounded in the specific deployment context.

Dylan Bouchard, Mohit Singh Chauhan, Zeya Ahmad et al.

Large language models have shown impressive capabilities in code generation, yet they often produce functionally incorrect code. Uncertainty quantification (UQ) methods have emerged as a promising approach for detecting hallucinations in natural language generation, but their effectiveness for code generation tasks remains underexplored. We systematically evaluate how UQ techniques transfer to code generation across three programming languages, five LLMs, and over 1,700 problems. We find that some token-probability-based methods generalize effectively without modification, while sampling-based methods relying on natural language inference (NLI) fail because NLI models cannot distinguish functionally different code, causing most responses to collapse into a single semantic cluster. To address this, we introduce functional equivalence methods, a family of code-specific methods that replace NLI-based semantic equivalence with an LLM-based functional equivalence assessment, including functional entropy, a code-specific analog of semantic entropy. Functional equivalence methods achieve top AUROC in 11 out of 15 model-benchmark combinations and the best calibration across most settings, consistently outperforming both NLI-based counterparts and all other methods evaluated.

Dylan Bouchard, Mohit Singh Chauhan, David Skarbrevik et al.

Large Language Models (LLMs) have been observed to exhibit bias in numerous ways, potentially creating or worsening outcomes for specific groups identified by protected attributes such as sex, race, sexual orientation, or age. To help address this gap, we introduce LangFair, an open-source Python package that aims to equip LLM practitioners with the tools to evaluate bias and fairness risks relevant to their specific use cases. The package offers functionality to easily generate evaluation datasets, comprised of LLM responses to use-case-specific prompts, and subsequently calculate applicable metrics for the practitioner's use case. To guide in metric selection, LangFair offers an actionable decision framework.

Dylan Bouchard, Mohit Singh Chauhan, Viren Bajaj et al.

Uncertainty quantification has emerged as an effective approach to closed-book hallucination detection for LLMs, but existing methods are largely designed for short-form outputs and do not generalize well to long-form generation. We introduce a taxonomy for fine-grained uncertainty quantification in long-form LLM outputs that distinguishes methods by design choices at three stages: response decomposition, unit-level scoring, and response-level aggregation. We formalize several families of consistency-based black-box scorers, providing generalizations and extensions of existing methods. In our experiments across multiple LLMs and datasets, we find 1) claim-response entailment consistently performs better or on par with more complex claim-level scorers, 2) claim-level scoring generally yields better results than sentence-level scoring, and 3) uncertainty-aware decoding is highly effective for improving the factuality of long-form outputs. Our framework clarifies relationships between prior methods, enables apples-to-apples comparisons, and provides practical guidance for selecting components for fine-grained UQ.

Dylan Bouchard

Model cascades, in which a cheap LLM defers to an expensive one on low-confidence queries, are widely used to navigate the cost-quality tradeoff at deployment. Existing approaches largely treat the deferral threshold as an empirical hyperparameter, with limited guidance on the geometry of the resulting cost-quality frontier over a model pool. We develop a decision-theoretic framework grounded in constrained optimization and duality. For a two-model cascade, we establish piecewise concavity of the cost-quality frontier on decreasing-benefit regions of the confidence support, with reciprocal shadow prices linking the budget- and quality-constrained formulations. Given a pool of $k$ models, we characterize the frontier achievable by deterministic two-model threshold cascades as the pointwise envelope over $\binom{k}{2}$ pairwise cascades, with switching points where the optimal pair changes. For $k$-model cascades, we derive first-order conditions in which a single shadow price equalizes marginal quality-per-cost across stage boundaries. We validate the framework on five benchmarks (MATH, MMLU, TriviaQA, SimpleQA, LiveCodeBench) across eight models from five providers. Within the deterministic threshold-cascade class, full fixed chains underperform the pairwise envelope, and optimized subsequence cascades do not deliver practically meaningful held-out gains over it. A lightweight pre-generation router exceeds the best cascade policy on four of five datasets, mainly because it avoids the cheap model's generation cost on queries sent directly to a larger model rather than because of a stronger routing signal. These results suggest that cascade performance is limited primarily by structural cost, since cascades pay the cheap model before any escalation decision, rather than by a shortage of intermediate stages.

Dylan Bouchard, Mohit Singh Chauhan, David Skarbrevik et al.

Hallucinations, defined as instances where Large Language Models (LLMs) generate false or misleading content, pose a significant challenge that impacts the safety and trust of downstream applications. We introduce UQLM, a Python package for LLM hallucination detection using state-of-the-art uncertainty quantification (UQ) techniques. This toolkit offers a suite of UQ-based scorers that compute response-level confidence scores ranging from 0 to 1. This library provides an off-the-shelf solution for UQ-based hallucination detection that can be easily integrated to enhance the reliability of LLM outputs.

Dylan Bouchard, Mohit Singh Chauhan

Hallucinations are a persistent problem with Large Language Models (LLMs). As these models become increasingly used in high-stakes domains, such as healthcare and finance, the need for effective hallucination detection is crucial. To this end, we outline a versatile framework for closed-book hallucination detection that practitioners can apply to real-world use cases. To achieve this, we adapt a variety of existing uncertainty quantification (UQ) techniques, including black-box UQ, white-box UQ, and LLM-as-a-Judge, transforming them as necessary into standardized response-level confidence scores ranging from 0 to 1. To enhance flexibility, we propose a tunable ensemble approach that incorporates any combination of the individual confidence scores. This approach enables practitioners to optimize the ensemble for a specific use case for improved performance. To streamline implementation, the full suite of scorers is offered in this paper's companion Python toolkit, UQLM. To evaluate the performance of the various scorers, we conduct an extensive set of experiments using several LLM question-answering benchmarks. We find that our tunable ensemble typically surpasses its individual components and outperforms existing hallucination detection methods. Our results demonstrate the benefits of customized hallucination detection strategies for improving the accuracy and reliability of LLMs.