Related papers: Incentivizing Quality Text Generation via Statistical Contracts

Related papers

COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization [55.60171725587438]
Large language model (LLM) agents can benefit from reusable skills distilled from prior task experience.<n>Existing skill optimization methods often rely on costly execution-based evaluation and substantial task data.<n>We introduce textbfCOBRA-Skills, an efficient framework that formulates skill optimization as budgeted sequential optimization over a dynamically evolving candidate space.
arXiv Detail & Related papers (2026-09-10T15:12:24Z)
ACEM: A Cost Estimation Model for Agentic Software Engineering [0.0]
This paper proposes ACEM (Agentic Cost Estimation Model), which decomposes total agentic development cost into three additive dimensions.<n> ACEM introduces three constructs for agentic dynamics: the Revision Factor (RF), modeling token overhead from output rejection and retries; the Context Factor (CF), capturing rising token consumption as context accumulates; and the HITL Intensity Score (HIS), a four-level oversight classification scheme.<n>As an early-stage proposal, it invites the research community to calibrate, test, and extend the model through real project data.
arXiv Detail & Related papers (2026-08-03T17:54:11Z)
VASO: Formally Verifiable Self-Evolving Skills for Physical AI Agents [57.240036084348354]
We introduce VASO, a framework for verification-guided self-evolution of robot skill contracts.<n>VASO verifies logically inconsistent skill contracts, then verifies plans induced by the skill against global and local temporal specifications.<n>On Clearpath Jackal and PX4 quadcopter tasks, VASO reaches 97.2% formal-specification compliance using fewer than 100 optimization samples.
arXiv Detail & Related papers (2026-06-03T20:02:35Z)
Cost-Ordered Feasibility for Multi-Armed Bandits with Cost Subsidy [17.48220873982007]
In applications, the goal is to minimize cost subject to a constraint on the minimum permissible reward, an objective captured by multi-armed bandits with cost-subsidy (MAB-CS)<n>We characterize the expected sub-optimal samples required by any policy by proving instance-dependent lower bounds.<n>Then, we propose an algorithm called Cost-Ordered Feasibility (COF) that intelligently combine samples from all arms to gauge the feasibility of a cheap arm.
arXiv Detail & Related papers (2026-05-08T03:07:25Z)
Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems [54.916243942641444]
Large language models (LLMs) are emerging as key enablers of automation in domains such as telecommunications.<n>We study an edge-cloud-expert cascaded LLM-based knowledge system that supports decision-making through a question-and-answer pipeline.
arXiv Detail & Related papers (2025-12-23T03:10:09Z)
Design and Evaluation of Cost-Aware PoQ for Decentralized LLM Inference [4.254924788681319]
This paper introduces a cost-aware Proof of Quality (PoQ) framework for decentralized large language model (LLM) inference.<n>The design combines ground truth token level F1, lightweight learned evaluators, and GPT based judgments within a unified evaluation pipeline.<n> Monte Carlo simulations over 5,000 PoQ rounds demonstrate that the cost-aware reward scheme consistently assigns higher average rewards to high quality low cost inference models.
arXiv Detail & Related papers (2025-12-18T08:57:17Z)
Do Large Language Models Respect Contracts? Evaluating and Enforcing Contract-Adherence in Code Generation [11.445615378917578]
PACT is a program assessment and contract-adherence evaluation framework.<n>It provides a comprehensive test-suite corpus focused on contract violations.<n>It enables a systematic analysis of code generation under varied prompting conditions.
arXiv Detail & Related papers (2025-10-14T01:12:37Z)
Curriculum-Guided Reinforcement Learning for Synthesizing Gas-Efficient Financial Derivatives Contracts [1.1565257196553245]
This paper introduces a Reinforcement Learning framework to generate smart contracts directly from Common Domain Model (CDM) specifications.<n>We employ a Proximal Policy Optimization (PPO) agent that learns to select optimal code snippets from a pre-defined library.<n>Our empirical results show the RL agent learns to generate contracts with significant gas savings, achieving cost reductions of up to 35.59% on unseen test data.
arXiv Detail & Related papers (2025-09-28T17:01:55Z)
Probabilistically Tightened Linear Relaxation-based Perturbation Analysis for Neural Network Verification [83.25968588249776]
We present a novel framework that combines over-approximation techniques from LiRPA-based approaches with a sampling-based method to compute tight intermediate reachable sets.<n>With negligible computational overhead, $textttPT-LiRPA$ exploiting the estimated reachable sets, significantly tightens the lower and upper linear bounds of a neural network's output.
arXiv Detail & Related papers (2025-07-07T18:45:53Z)
Economic Evaluation of LLMs [0.9208007322096532]
We show that reasoning models offer better accuracy-cost tradeoffs as soon as the economic cost of a mistake exceeds $0.01.<n>We find that single large LLMs often outperform cascades when the cost of making a mistake is as low as $0.1.
arXiv Detail & Related papers (2025-07-04T23:16:02Z)
Cost-Optimal Active AI Model Evaluation [71.2069549142394]
Development of generative AI systems requires continual evaluation, data acquisition, and annotation.<n>We develop novel, cost-aware methods for actively balancing the use of a cheap, but often inaccurate, weak rater.<n>We derive a family of cost-optimal policies for allocating a given annotation budget between weak and strong raters.
arXiv Detail & Related papers (2025-06-09T17:14:41Z)
Designing DSIC Mechanisms for Data Sharing in the Era of Large Language Models [0.0]
Training large language models (LLMs) requires vast amounts of high-quality data from institutions that face legal, privacy, and strategic constraints.<n>We introduce a mechanism-design framework for truthful, trust-minimized data sharing.<n>We formalize a model where providers privately know their data cost and quality, and value arises solely from the data's contribution to model performance.
arXiv Detail & Related papers (2025-06-01T22:17:18Z)
Supervised Optimism Correction: Be Confident When LLMs Are Sure [91.7459076316849]
We establish a novel theoretical connection between supervised fine-tuning and offline reinforcement learning. We show that the widely used beam search method suffers from unacceptable over-optimism. We propose Supervised Optimism Correction, which introduces a simple yet effective auxiliary loss for token-level $Q$-value estimations.
arXiv Detail & Related papers (2025-04-10T07:50:03Z)
Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs [60.881609323604685]
Large Language Models (LLMs) accessed via black-box APIs introduce a trust challenge. Users pay for services based on advertised model capabilities. providers may covertly substitute the specified model with a cheaper, lower-quality alternative to reduce operational costs. This lack of transparency undermines fairness, erodes trust, and complicates reliable benchmarking.
arXiv Detail & Related papers (2025-04-07T03:57:41Z)
CoKe: Customizable Fine-Grained Story Evaluation via Chain-of-Keyword Rationalization [90.15027447565427]
Chain of thought (CoT) generates free-text explanations that help guide a model's predictions. Self-Consistency (SC) marginalizes predictions over multiple generated explanations. We propose $textbfC$hain-$textbfo$f-$textbfKe$ywords (CoKe)
arXiv Detail & Related papers (2025-03-21T13:37:46Z)
How Humans Help LLMs: Assessing and Incentivizing Human Preference Annotators [8.244694683982784]
We investigate the questions of assessing the performance of human annotators and incentivizing them to provide high-quality annotations. We develop a principal-agent model to characterize the behaviors of and the interactions between the company and the human annotators. The model rationalizes a practical mechanism of a bonus scheme to incentivize annotators which benefits both parties.
arXiv Detail & Related papers (2025-02-10T12:15:27Z)
Auto-PRE: An Automatic and Cost-Efficient Peer-Review Framework for Language Generation Evaluation [52.76508734756661]
Auto-PRE is an automatic evaluation framework inspired by the peer review process.<n>Unlike previous approaches that rely on human annotations, Auto-PRE automatically selects evaluators based on three core traits.<n> Experiments on three representative tasks, including summarization, non-factoid QA, and dialogue generation, demonstrate that Auto-PRE achieves state-of-the-art performance.
arXiv Detail & Related papers (2024-10-16T06:06:06Z)
Contractual Reinforcement Learning: Pulling Arms with Invisible Hands [68.77645200579181]
We propose a theoretical framework for aligning economic interests of different stakeholders in the online learning problems through contract design. For the planning problem, we design an efficient dynamic programming algorithm to determine the optimal contracts against the far-sighted agent. For the learning problem, we introduce a generic design of no-regret learning algorithms to untangle the challenges from robust design of contracts to the balance of exploration and exploitation.
arXiv Detail & Related papers (2024-07-01T16:53:00Z)
New Perspectives in Online Contract Design [2.296475290901356]
This work studies the repeated principal-agent problem from an online learning perspective. The principal's goal is to learn the optimal contract that maximizes her utility through repeated interactions.
arXiv Detail & Related papers (2024-03-11T20:28:23Z)
$\texttt{COSMIC}$: Mutual Information for Task-Agnostic Summarization Evaluation [39.287235598507294]
We propose a novel task-oriented evaluation approach that assesses summarizers based on their capacity to produce summaries that are useful for downstream tasks, while preserving task outcomes. We introduce $textttCOSMIC$ as a practical implementation of this metric, demonstrating its strong correlation with human judgment-based metrics and its effectiveness in predicting downstream task performance.
arXiv Detail & Related papers (2024-02-29T18:51:23Z)
Incentivized Truthful Communication for Federated Bandits [61.759855777522255]
We propose an incentive compatible (i.e., truthful) communication protocol, named Truth-FedBan. We show that Truth-FedBan still guarantees the sub-linear regret and communication cost without any overheads.
arXiv Detail & Related papers (2024-02-07T00:23:20Z)
Assistive Large Language Model Agents for Socially-Aware Negotiation Dialogues [47.977032883078664]
We develop assistive agents based on Large Language Models (LLMs) We simulate business negotiations by letting two LLM-based agents engage in role play. A third LLM acts as a remediator agent to rewrite utterances violating norms for improving negotiation outcomes.
arXiv Detail & Related papers (2024-01-29T09:07:40Z)
Sentiment Analysis through LLM Negotiations [58.67939611291001]
A standard paradigm for sentiment analysis is to rely on a singular LLM and makes the decision in a single round. This paper introduces a multi-LLM negotiation framework for sentiment analysis.
arXiv Detail & Related papers (2023-11-03T12:35:29Z)
Automating construction contract review using knowledge graph-enhanced large language models [1.50580995941543]
This paper investigates whether integrating Large Language Models (LLMs) and Knowledge Graphs (KGs) can enhance the accuracy and interpretability of automated contract risk identification.<n>A tuning-free approach is proposed that integrates LLMs with a Nested Contract Knowledge Graph (NCKG) using a Graph Retrieval-Augmented Generation (GraphRAG) framework for contract knowledge retrieval and reasoning.<n>Tested on international EPC contracts, the method achieves more accurate risk evaluation and interpretable risk summaries than baseline models.
arXiv Detail & Related papers (2023-09-21T14:53:36Z)
Estimating and Incentivizing Imperfect-Knowledge Agents with Hidden Rewards [4.742123770879715]
In practice, incentive providers often cannot observe the reward realizations of incentivized agents. This paper explores a repeated adverse selection game between a self-interested learning agent and a learning principal. We introduce an estimator whose only input is the history of principal's incentives and agent's choices.
arXiv Detail & Related papers (2023-08-13T08:12:01Z)
Delegated Classification [21.384062337682185]
We propose a theoretical framework for incentive-aware delegation of machine learning tasks. We define budget-optimal contracts and prove they take a simple threshold form under reasonable assumptions. Empirically, we demonstrate that budget-optimal contracts can be constructed using small-scale data.
arXiv Detail & Related papers (2023-06-20T11:59:03Z)
ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts [39.75232199445175]
We propose "document-level natural language inference (NLI) for contracts" A system is given a set of hypotheses and a contract, and it is asked to classify whether each hypothesis is "entailed by", "contradicting to" or "not mentioned by" (neutral to) the contract. We release the largest corpus to date consisting of 607 annotated contracts.
arXiv Detail & Related papers (2021-10-05T03:22:31Z)
Measuring Association Between Labels and Free-Text Rationales [60.58672852655487]
In interpretable NLP, we require faithful rationales that reflect the model's decision-making process for an explained instance. We demonstrate that pipelines, existing models for faithful extractive rationalization on information-extraction style tasks, do not extend as reliably to "reasoning" tasks requiring free-text rationales. We turn to models that jointly predict and rationalize, a class of widely used high-performance models for free-text rationalization whose faithfulness is not yet established.
arXiv Detail & Related papers (2020-10-24T03:40:56Z)
Cost-Sensitive Portfolio Selection via Deep Reinforcement Learning [100.73223416589596]
We propose a cost-sensitive portfolio selection method with deep reinforcement learning. Specifically, a novel two-stream portfolio policy network is devised to extract both price series patterns and asset correlations. A new cost-sensitive reward function is developed to maximize the accumulated return and constrain both costs via reinforcement learning.
arXiv Detail & Related papers (2020-03-06T06:28:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.