LLM Inference

LLM: Large Language Model

Overview

Large language model inference is the process of turning prompts into outputs, and its speed, cost, reliability, and privacy shape what applications can use models in practice. Systems work optimizes prefill and token-by-token decoding through KV-cache management, batching and scheduling, parallelism, quantization, and specialized GPU, mobile, or edge kernels. Another strand changes generation at test time using speculative decoding, early exit, retrieval, or repeated reasoning paths to trade extra computation for better accuracy or confidence. The central challenge is that these trade-offs depend heavily on workload, hardware, and inference backend, making reproducible benchmarks and methods that preserve quality while reducing latency, memory, and energy ongoing priorities.

Latest papers

321 papers43 papers in the last four weeks, up 8% on the four weeks before. 0.3% of all new papers.

Feb 27, 2026

PREBA: Surgical Duration Prediction via PCA-Weighted Retrieval-Augmented LLMs and Bayesian Averaging Aggregation

Accurate prediction of surgical duration is pivotal for hospital resource management. Although recent supervised learning approaches, from machine learning (ML) to fine-tuned large language models (LLMs), have shown strong performance, they remain constrained by the need for high-quality labeled data and computationally intensive training. In contrast, zero-shot LLM inference offers a promising training-free alternative, but it lacks grounding in institution-specific clinical evidence, making its predictions clinically misaligned and prone to instability. To address these limitations, we present PREBA, a retrieval-augmented framework that integrates PCA-weighted retrieval and Bayesian averaging to ground LLM reasoning in institution-specific evidence without requiring task-specific fine-tuning. Specifically, PREBA first encodes heterogeneous clinical features into a unified representation. It then performs PCA-weighted retrieval, weighting each dimension by its contribution to the variation across institutional cases, instead of treating them as equally informative, and conditions the LLM to generate multiple candidate predictions. Finally, Bayesian averaging consolidates these predictions with population-level statistical priors, yielding a calibrated estimate that remains stable and clinically plausible. We evaluate PREBA on four real-world datasets spanning different institutions and languages, using three state-of-the-art LLMs, including Qwen3, DeepSeek-R1, and HuatuoGPT-o1. PREBA consistently outperforms zero-shot inference, reducing MAE by up to 64.9% and raising R2 to as high as 0.63. It further attains accuracy competitive with, and on several datasets superior to, fully supervised ML methods, while offering greater interpretability through retrieved exemplars and explicit priors. The code is available at https://github.com/kanxueli/PREBA.
Feb 27, 2026

SLA-Aware Distributed LLM Inference Across Device-RAN-Cloud

Embodied AI requires sub-second inference near the Radio Access Network (RAN), but deployments span heterogeneous tiers (on-device, RAN-edge, cloud) and must not disrupt real-time baseband processing. We report measurements from a 5G Standalone (SA) AI-RAN testbed using a fixed baseline policy for repeatability. The setup includes an on-device tier, a three-node RAN-edge cluster co-hosting a containerized 5G RAN, and a cloud tier. We find that on-device execution remains multi-second and fails to meet sub-second budgets. At the RAN edge, SLA feasibility is primarily determined by model variant choice: quantized models concentrate below 0.5,s, while unquantized and some larger quantized models incur deadline misses due to stalls and queuing. In the cloud tier, meeting a 0.5,s deadline is challenging on the measured WAN path (up to 32.9% of requests complete within 0.5,s), but all evaluated variants meet a 1.0,s deadline (100% within 1.0,s). Under saturated downlink traffic and up to N=20N{=}20 concurrent inference clients, Multi-Instance GPU (MIG) isolation preserves baseband timing-health proxies, supporting safe co-location under fixed partitioning.
Feb 26, 2026

Empirical Characterization of Inference-Time Elicited Probability Transformations in Large Language Models

Large language models increasingly rely on inference-time procedures such as chain-of-thought reasoning, self-refinement, retrieval augmentation, and verifier-guided revision, yet the structure of elicited probability transformations under these procedures remains poorly understood. We study externally elicited probability assignments over candidate answers and observe recurring approximate log-ratio relationships: log⁡q~t(i)=αt(log⁡qt(i)+log⁡bt(i))+ct,\log \tilde q_t(i) = α_t \left( \log q_t(i) + \log b_t(i) \right) + c_t, where qtq_t and q~t\tilde q_t are pre- and post-elicitation probabilities, btb_t is an externally constructed evidence signal, and αtα_t is an empirical descriptor of the prompting configuration. Across 4,975 reasoning problems from GPQA Diamond, TheoremQA, MMLU-Pro, and ARC-Challenge, evaluated on multiple instruction-tuned model families, we observe approximate log-ratio relationships with mean R2≈0.76R^2 \approx 0.76 over about 1.3×1051.3 \times 10^5 candidate-level observations. Coefficients vary across elicitation settings, but qualitatively similar relationships persist across evaluated conditions. Robustness analyses using alternative statistical representations, prompting configurations, held-out evaluation, and token-level log-probabilities suggest that the observed structure is not tied to one prompting procedure or probability estimation method. The main contribution is not the algebraic form itself, which is related to generalized Bayesian updating and probability-transformation frameworks, but the empirical observation that diverse inference-time prompting pipelines repeatedly exhibit reproducible log-ratio structure under controlled conditions. The framework provides a protocol-sensitive perspective for analyzing calibration, evidence amplification, uncertainty propagation, and interaction sensitivity in inference-time LLM pipelines.
Feb 25, 2026

Sustainable LLM Inference using Context-Aware Model Switching

Large language models have become central to many AI applications, but their growing energy consumption raises serious sustainability concerns. A key limitation in current AI deployments is the reliance on a one-size-fits-all inference strategy where most systems route every request to the same large model, regardless of task complexity, leading to substantial and unnecessary energy waste. To address this issue, we propose a context-aware model switching approach that dynamically selects an appropriate language model based on query complexity. The proposed system uses a Context-Aware Model Switching for Energy-Efficient LLM Inference that combines caching for repeated queries, rulebased complexity scoring for fast and explainable decisions, machine learning classification to capture semantic intent, and a user-adaptive component that learns from interaction patterns over time. The proposed architecture was evaluated using real conversation workloads and three open-source language models (Gemma3 1B, Gemma3 4B and Qwen3 4B) with different computational costs, measuring energy consumption (via NVML GPU power telemetry), response latency, routing accuracy, and output quality (BERTScore F1) to reflect real-world usage conditions. Experimental results show that the model switching approach can reduce energy consumption by up to 67.5% compared to always using the largest model while maintaining a response quality of 93.6%. In addition, the response time for simple queries also improved significantly by approximately 68%. These results show that model switching inference offers a practical and scalable path toward more energy-efficient and sustainable AI systems, demonstrating that significant efficiency gains can be achieved without major sacrifices in response quality.
Feb 20, 2026

RPU -- A Reasoning Processing Unit

Large language model (LLM) inference performance is increasingly bottlenecked by the memory wall. While GPUs continue to scale raw compute throughput, they struggle to deliver scalable performance for memory bandwidth bound workloads. This challenge is amplified by emerging reasoning LLM applications, where long output sequences, low arithmetic intensity, and tight latency constraints demand significantly higher memory bandwidth. As a result, system utilization drops and energy per inference rises, highlighting the need for an optimized system architecture for scalable memory bandwidth. To address these challenges we present the Reasoning Processing Unit (RPU), a chiplet-based architecture designed to address the challenges of the modern memory wall. RPU introduces: (1) A Capacity-Optimized High-Bandwidth Memory (HBM-CO) that trades capacity for lower energy and cost; (2) a scalable chiplet architecture featuring a bandwidth-first power and area provisioning design; and (3) a decoupled microarchitecture that separates memory, compute, and communication pipelines to sustain high bandwidth utilization. Simulation results show that RPU performs up to 45.3x lower latency and 18.6x higher throughput over an H100 system at ISO-TDP on Llama3-405B.
Feb 19, 2026

Privacy-Preserving Mechanisms Enable Cheap Verifiable Inference of LLMs

As large language models (LLMs) continue to grow in size, fewer users are able to host and run models locally. This has led to increased use of third-party hosting services. However, in this setting, there is a lack of guarantees on the computation performed by the inference provider. For example, a dishonest provider may replace an expensive large model with a cheaper-to-run weaker model and return the results from the weaker model to the user. Existing tools to verify inference typically rely on methods from cryptography such as zero-knowledge proofs (ZKPs), but these add significant computational overhead, and remain infeasible for use for large models. In this work, we develop a new insight -- that given a method for performing private LLM inference, one can obtain forms of verified inference at marginal extra cost. Specifically, we propose two new protocols which leverage privacy-preserving LLM inference in order to provide guarantees over the inference that was carried out. Our approaches are cheap, requiring the addition of a few extra tokens of computation, and have little to no downstream impact. As the fastest privacy-preserving inference methods are typically faster than ZK methods, the proposed protocols also improve verification runtime. Our work provides novel insights into the connections between privacy and verifiability in LLM inference.
Feb 13, 2026

TensorCommitments: A Lightweight Verifiable Inference for Large Language Models

Most large language models (LLMs) run on external clouds: users send a prompt, pay for inference, and must trust that the remote GPU executes the LLM without any adversarial tampering. We critically ask how to achieve verifiable LLM inference, where a prover (the service) must convince a verifier (the client) that an inference was run correctly without rerunning the LLM. Existing cryptographic works are too slow at the LLM scale, while non-cryptographic ones require a strong verifier GPU. We propose TensorCommitments (TCs), a tensor-native proof-of-inference scheme. TC binds the LLM inference to a commitment, an irreversible tag that breaks under tampering, organized in our multivariate Terkle Trees. For LLaMA2, TC adds only 0.97% prover and 0.12% verifier time over inference while improving robustness to tailored attacks by up to 48% over the best prior work requiring a verifier GPU.
Feb 8, 2026

The Hidden Cost of Structured Generation in LLMs: Draft-Conditioned Constrained Decoding

Large language models (LLMs) are increasingly used to generate executable outputs, JSON objects, and API calls, where a single syntax error can make the output unusable. Constrained decoding enforces validity token-by-token via masking and renormalization, but it can distort generation when the model assigns low probability mass to valid continuations, pushing decoding toward locally valid yet semantically incorrect trajectories. We propose Draft-Conditioned Constrained Decoding (DCCD), a simple two-step, training-free inference procedure that decouples semantic planning from structural enforcement: an unconstrained draft is generated first, and constrained decoding is then applied, conditioned on this draft, to guarantee validity. We analyze DCCD through a KL-projection view, showing that draft conditioning increases feasible mass and reduces the cumulative "projection tax" induced by hard constraints, with an optional best-of-KK draft selection. Across structured reasoning benchmarks, DCCD improves strict structured accuracy by up to +24 percentage points over standard constrained decoding (e.g., 15.2% to 39.0% on GSM8K with a 1B model), and enables smaller model pairs to match or exceed much larger constrained baselines, yielding substantial gains in parameter efficiency.
Feb 2, 2026

vLLM Hook v1: A Plug-in for Programming Model Internals on vLLM

Modern artificial intelligence models are deployed on inference engines to optimize runtime efficiency and resource allocation, particularly for transformer-based large language models. The vLLM project is a major open-source library to support model serving and inference. However, the current implementation of vLLM limits programmability of the internal states of deployed models. This prevents the use of popular test-time model alignment and enhancement methods. For example, it prevents the detection of adversarial prompts based on attention patterns or the adjustment of model responses based on activation steering. To bridge this critical gap, we present vLLM Hook, an opensource plug-in to enable the programming of internal states for vLLM models. Based on a configuration file specifying which internal states to capture, vLLM Hook provides seamless integration to vLLM and supports two essential features: passive programming and active programming. For passive programming, vLLM Hook probes the selected internal states for subsequent analysis, while keeping the model generation intact. For active programming, vLLM Hook enables efficient intervention of model generation by altering the selected internal states. In version 1 (named vLLM Hook MIA), the plugin runs on vLLM's V2 model runner and preserves the engine's CUDA graphs, so that capturing and steering internal states incurs only a small decoding overhead. It supports both offline use and serving through vllm serve. In addition to presenting the core functions of vLLM Hook, we demonstrate use cases including prompt injection detection, attention-based re-ranking for retrieval-augmented generation, activation steering, hidden-state probing, hallucination detection, schema linking for text-to-SQL, and tool-call risk assessment. Finally, we welcome the community's contribution to improve vLLM Hook via https://github.com/IBM/vLLM-Hook.
Jan 29, 2026

Test-Time Compute Games

Test-time compute has emerged as a promising strategy to enhance the reasoning abilities of large language models (LLMs). However, this strategy has in turn increased how much users pay cloud-based providers offering LLM-as-a-service, since providers charge users for the amount of test-time compute they use to generate an output. In our work, we show that the market of LLM-as-a-service is socially inefficient: providers have a financial incentive to increase the amount of test-time compute, even if this increase contributes little to the quality of the outputs. To address this inefficiency, we introduce a reverse second-price auction mechanism where providers bid their offered price and (expected) quality for the opportunity to serve a user, and users pay proportionally to the marginal value generated by the winning provider relative to the second-highest bidder. To illustrate and complement our theoretical results, we conduct experiments with multiple instruct models from the Llama\texttt{Llama} and Qwen\texttt{Qwen} families, as well as reasoning models distilled from DeepSeek-R1\texttt{DeepSeek-R1}, on math and science benchmark datasets.
Jan 29, 2026

LAMP: Look-Ahead Mixed-Precision Inference of Large Language Models

Mixed-precision computations are a hallmark of the current stage of AI, driving the progress in large language models towards efficient, locally deployable solutions. This article addresses the floating-point computation of compositionally-rich functions, concentrating on transformer inference. Based on the rounding error analysis of a composition f(g(x))f(g(\mathrm{x})), we provide an adaptive strategy that selects a small subset of components of g(x)g(\mathrm{x}) to be computed more accurately while all other computations can be carried out with lower accuracy. We then explain how this strategy can be applied to different compositions within a transformer and illustrate its overall effect on transformer inference. We study the effectiveness of this algorithm numerically on GPT-2 models and demonstrate that already very low recomputation rates allow for improvements of up to two orders of magnitude in accuracy.
Jan 29, 2026

Large Language Models Naively Recover Ethnicity from Individual Records

I demonstrate that large language models can infer ethnicity from names with accuracy exceeding that of Bayesian Improved Surname Geocoding (BISG) without additional training data, enabling inference outside the United States and to contextually appropriate classification categories. Using stratified samples from Florida and North Carolina voter files with self-reported race, LLM-based classification achieves up to 84.7% accuracy, outperforming BISG (68.2%) on balanced samples. I test six models including Gemini 3 Flash, GPT-4o, and open-source alternatives such as DeepSeek v3.2 and GLM-4.7. Enabling extended reasoning can improve accuracy by 1-3 percentage points, though effects vary across contexts; including metadata such as party registration reaches 86.7%. LLM classification also reduces the income bias inherent in BISG, where minorities in wealthier neighborhoods are systematically misclassified as White. I further validate using Lebanese voter registration with religious sect (64.3% accuracy), Indian MPs from reserved constituencies (99.2%), and Indian land records with caste classification (74.0%). Aggregate validation across India, Uganda, Nepal, Armenia, Chile, and Costa Rica using original full-count voter rolls demonstrates that the method recovers known population distributions where naming conventions are distinctive. For large-scale applications, small transformer models fine-tuned on LLM labels exceed BISG accuracy while enabling local deployment at no cost.
Dec 25, 2025

Analysis of LLM Vulnerability to GPU Soft Errors: An Instruction-Level Fault Injection Study

Large language models (LLMs) are highly compute- and memory-intensive, posing significant demands on high-performance GPUs. At the same time, advances in GPU technology driven by shrinking transistor sizes and lower operating voltages have made these devices increasingly susceptible to soft errors, particularly in radiation-prone environments such as satellite computing scenarios. While prior work has examined GPU soft errors, most studies have focused on general-purpose applications or conventional neural networks primarily used for vision tasks such as classification and detection. However, vulnerability analysis of modern LLMs remains limited, despite their rapid adoption in diverse application scenarios. Given the unique characteristics of LLMs, their resilience to soft errors may differ substantially from earlier models. To bridge this gap, we conduct the first instruction-level fault injection study of LLM inference to analyze the factors affecting LLM vulnerability. Our approach reveals reliability characteristics from multiple perspectives, highlighting the effects of model architecture, parameter scale, and task complexity. These findings provide new insights into LLM reliability and inform the design of more effective fault tolerance mechanisms.
Nov 13, 2025

Scalable Synthesis of distributed LLM workloads through Symbolic Tensor Graphs

Optimizing the performance of large language models (LLMs) on large-scale AI training and inference systems requires a scalable and expressive mechanism to model distributed workload execution. Such modeling is essential for pre-deployment system-level optimizations (e.g., parallelization strategies) and hardware design-space explorations. While recent efforts have proposed collecting execution traces from real systems, access to large-scale infrastructure remains limited to major cloud providers. Moreover, traces capturing execution on a specific platform cannot be easily adapted to study alternate software and/or hardware configurations, especially at scale. We introduce STAGE, a framework that synthesizes high-fidelity execution graphs to accurately model distributed AI workloads (including LLMs and MoEs). STAGE supports a comprehensive set of parallelization strategies, allowing users to systematically explore a wide spectrum of model architectures and system configurations. STAGE demonstrates its scalability by synthesizing high-fidelity LLM traces spanning over 128K GPUs, while preserving tensorlevel accuracy in compute, memory, and communication. STAGE is publicy available at https://github.com/astra-sim/stage
Nov 5, 2025

Beyond Reasoning: RL-Policy Guided LLM Inference for Efficient Strategy in Liar's Poker

AI researchers have long focused on poker-like games as a testbed for environments characterized by multi-player dynamics, imperfect information, and reasoning under uncertainty. While recent breakthroughs have matched elite human play at no-limit Texas hold'em, the multi-player dynamics are subdued: most hands converge quickly with only two players engaged through multiple rounds of bidding. In this paper, we present Solly, the first AI agent to achieve elite human play in reduced-format Liar's Poker, a game characterized by extensive multi-player engagement. We trained Solly using self-play with a model-free, actor-critic, deep reinforcement learning algorithm. Solly played at an elite human level as measured by win rate (won over 50% of hands) and equity (money won) in heads-up and multi-player Liar's Poker. Solly also outperformed large language models (LLMs), including those with reasoning abilities, on the same metrics. Solly developed novel bidding strategies, randomized play effectively, and was not easily exploitable by world-class human players. In one extension, when Solly's policies were provided to LLMs as a domain-specific guide for inference, LLM performance improved and token costs decreased. This result suggests that low-cost RL agents can be used to boost LLM efficiency and reasoning capabilities.
Oct 3, 2025

Best-of-Majority: Minimax-Optimal Strategy for Pass@kk Inference Scaling

LLM inference often generates a batch of candidates for a prompt and selects one via strategies like majority voting or Best-of- N (BoN). For difficult tasks, this single-shot selection often underperforms. Consequently, evaluations commonly report Pass@kk: the agent may submit up to kk responses, and only the best of them is used when computing regret. Motivated by this, we study inference scaling in the more general Pass@kk inference setting, and prove that neither majority voting nor BoN exhibits the desirable scaling with kk and the sampling budget NN. Combining the advantages of majority voting and BoN, we propose a new inference strategy called Best-of-Majority (BoM), with a pivotal step that restricts the candidates to the responses with high frequency in the NN samples before selecting the top-kk rewards. We prove that when the sampling budget is N=Ω~(C∗)N=\tildeΩ(C^*), the regret of BoM is O(εopt+εRM2C∗/k)O(ε_{\mathrm{opt}}+\sqrt{ε_{\mathrm{RM}}^2C^*/k}), where C∗C^* is the coverage coefficient, εRMε_{\mathrm{RM}} is the estimation error of the reward model, and εoptε_{\mathrm{opt}} is the estimation error of reward at the optimal response. We further establish a matching lower bound, certifying that our algorithm is minimax optimal. Beyond optimality, BoM has a key advantage: unlike majority voting and BoN, its performance does not degrade when increasing NN. Experimental results of inference on math problems show BoM outperforming both majority voting and BoN.
Jul 9, 2025

On the Effect of Uncertainty on Layer-wise Inference Dynamics

Understanding how large language models (LLMs) internally represent and process their predictions is central to detecting uncertainty and preventing hallucinations. While several studies have shown that models encode uncertainty in their hidden states, it is underexplored how this affects the way they process such hidden states. In this work, we demonstrate that the dynamics of output token probabilities across layers for certain and uncertain outputs are largely aligned, revealing that uncertainty does not seem to affect inference dynamics. Specifically, we use the Tuned Lens, a variant of the Logit Lens, to analyze the layer-wise probability trajectories of final prediction tokens across 11 datasets and 5 models. Using incorrect predictions as those with higher epistemic uncertainty, our results show aligned trajectories for certain and uncertain predictions that both observe abrupt increases in confidence at similar layers. We balance this finding by showing evidence that more competent models may learn to process uncertainty differently. Our findings challenge the feasibility of leveraging simplistic methods for detecting uncertainty at inference. More broadly, our work demonstrates how interpretability methods may be used to investigate the way uncertainty affects inference.
Apr 7, 2025

Prima.cpp: Fast 30-70B LLM Inference on Heterogeneous and Low-Resource Home Clusters

On-device inference offers privacy, offline use, and instant response, but consumer hardware restricts large language models (LLMs) to low throughput and capability. To overcome this challenge, we present prima.cpp, a distributed on-device inference system that runs 30-70B LLMs on consumer home clusters with mixed CPUs/GPUs, insufficient RAM/VRAM, slow disks, Wi-Fi links, and heterogeneous OSs. We introduce pipelined-ring parallelism (PRP) to overlap disk I/O with compute and communication, and address the prefetch-release conflict in mmap-based offloading. We further propose Halda, a heterogeneity-aware scheduler that co-optimizes per-device CPU/GPU workloads and device selection under RAM/VRAM constraints. On four consumer home devices, a 70B model reaches 674 ms/token TPOT with <6% memory pressure, and a 32B model with speculative decoding achieves 26 tokens/s. Compared with llama.cpp, exo, and dllama, our proposed prima.cpp achieves 5-17 times lower TPOT, supports fine-grained model sizes from 8B to 70B, ensures broader cross-OS and quantization compatibility, and remains OOM-free, while also being Wi-Fi tolerant, privacy-preserving, and hardware-independent. The code is available at https://github.com/OpenCPIL/prima.cpp.
Jan 16, 2025

Foundations of Large Language Models

This is a book about large language models. As indicated by the title, it primarily focuses on foundational concepts rather than comprehensive coverage of all cutting-edge technologies. The book is structured into six main chapters, each exploring a key area: pre-training, generative models, prompting, alignment, inference, and reasoning. It is intended for college students, professionals, and practitioners in natural language processing and related fields, and can serve as a reference for anyone interested in large language models.
Nov 12, 2024

Saving GPU Hours in LLM Inference System Development and Online Workloads with Simulation and DBMS-Inspired Cache Replacement Policies

LLMs are increasingly used world-wide from daily tasks to agentic systems and data analytics, requiring significant GPU resources. While LLM inference systems are capable of serving millions of requests from multiple users, they often lack theoretical models to determine whether they achieve the performance upper bounds of underlying hardware resources. Beyond online workload serving, merely analyzing existing systems-or developing yet another one-is both GPU-intensive and labor-intensive. This paper provides a comprehensive survey of LLM inference systems, focusing on their cache management policies and availability. We then show that simulations can be an effective tool to save GPU hours in the development and analysis phase of inference systems, revealing useful insights for developing better inference techniques, unlike how existing studies used simulations to find the best parameters inside a given system. Finally, we provide theoretical tools to estimate the optimal performance and formulate new ideas. Based on the theoretical analysis, especially on the cache management in LLM inference, we propose a simple yet effective cache replacement policy that can be easily plugged into existing preemptive schedulers and systems. We show that such a simple policy inspired from database systems can substantially save GPU hours in actual inference systems on online workloads. We share our experience submitting a journal paper to a database venue in November 2025 for anyone considering a similar path.
Feb 28, 2024

Few-Shot Fairness: Unveiling LLM's Potential for Fairness-Aware Classification

Large Language Models (LLMs) are increasingly being employed for downstream tasks such as tabular classification, where predictions can directly influence individuals in high-stakes domain such as hiring, education and criminal justice. As the adoption of LLMs for such decision making tasks continues to grow, ensuring fairness in their predictions becomes increasingly important. Existing approaches to ensure fairness in tabular data, typically process test instances independently, limiting the models awareness of the demographic composition and predictions of other instances, which is particularly important for reasoning about group-level fairness. To address this limitation, we propose FABLE (FAir Batch-based LLM framEwork) for tabular classification, a batch-based framework that jointly processes multiple test instances, enabling LLMs to reason over demographic information and prediction outcomes within a batch. To mitigate positional bias introduced by batch processing, the framework generates multiple shuffled versions of each batch and aggregates the resulting predictions through voting. We evaluate FABLE on three tabular classification datasets using three popular LLMs and four prompting configurations spanning zero-shot, few-shot, direct, and self-reflective prompting. Experimental results demonstrate that incorporating demographic information and explicit fairness constraints enable LLMs to achieve substantial fairness improvements across diverse datasets and fairness notions, highlighting their potential as fairness reasoners for tabular classification and promoting more equitable and accountable decision-making.