相关论文: Correcting Selection Bias in Sparse User Feedback …

As language models (LMs) become increasingly powerful and widely used, it is important to quantify them for sociodemographic bias with potential for harm. Prior measures of bias are sensitive to perturbations in the templates designed to…

Detecting cognitive biases in large language models (LLMs) is a fascinating task that aims to probe the existing cognitive biases within these models. Current methods for detecting cognitive biases in language models generally suffer from…

As large language models (LLMs) have been used in many downstream tasks, the internal stereotypical representation may affect the fairness of the outputs. In this work, we introduce human knowledge into natural language interventions and…

Error attribution in Large Language Model (LLM) multi-agent systems presents a significant challenge in debugging and improving collaborative AI systems. Current approaches to pinpointing agent and step level failures in interaction traces…

Generating high-quality summaries for chat dialogs often requires large labeled datasets. We propose a method to efficiently use unlabeled data for extractive summarization of customer-agent dialogs. In our method, we frame summarization as…

Mislabeled, duplicated, or biased data in real-world scenarios can lead to prolonged training and even hinder model convergence. Traditional solutions prioritizing easy or hard samples lack the flexibility to handle such a variety…

Aligning large language models (LLMs) to human preferences typically relies on aggregating pooled feedback into a single reward model. However, this standard approach assumes that all labelers share the same underlying preferences, ignoring…

Hierarchical statistical models are widely employed in information science and data engineering. The models consist of two types of variables: observable variables that represent the given data and latent variables for the unobservable…

Large language models (LLMs) are increasingly used for automated tutoring, but their reliability in structured symbolic domains remains unclear. We study step-level feedback for propositional logic proofs, which require precise symbolic…

Human annotations are an important source of information in the development of natural language understanding approaches. As under the pressure of productivity annotators can assign different labels to a given text, the quality of produced…

Performance of Large Language Models (LLMs) on multiple-choice tasks differs markedly between symbol-based and cloze-style evaluation formats. The observed discrepancies are systematically attributable to task characteristics: natural…

Noisy labeled data is more a norm than a rarity for crowd sourced contents. It is effective to distill noise and infer correct labels through aggregation results from crowd workers. To ensure the time relevance and overcome slow responses…

Multi-agent deliberation systems using large language models (LLMs) are increasingly proposed for policy simulation, yet they suffer from artificial consensus: evaluator agents converge on the same option regardless of their assigned value…

Large Language Models (LLMs), though shown to be effective in many applications, can vary significantly in their response quality. In this paper, we investigate this problem of prompt fairness: specifically, the phrasing of a prompt by…

Pre-ranking is a critical stage in industrial recommendation systems, tasked with efficiently scoring thousands of recalled items for downstream ranking. A key challenge is the train-serving discrepancy: pre-ranking models are trained only…

Mitigating social bias in large language models (LLMs) has become an increasingly important research objective. However, existing debiasing methods often incur high human and computational costs, exhibit limited effectiveness, and struggle…

State-of-the-art neural language models (LMs) represented by Transformers are highly complex. Their use of fixed, deterministic parameter estimates fail to account for model uncertainty and lead to over-fitting and poor generalization when…

The quality of machine learning models depends heavily on their training data. Selecting high-quality, diverse training sets for large language models (LLMs) is a difficult task, due to the lack of cheap and reliable quality metrics. While…

This study examines how Large Language Models (LLMs) perform when tackling quantitative management decision problems in a zero-shot setting. Drawing on 900 responses generated by five leading models across 20 diverse managerial scenarios,…

As Large Language Models (LLMs) transition from standalone chat interfaces to foundational reasoning layers in multi-agent systems and recursive evaluation loops (LLM-as-a-judge), the detection of durable, provider-level behavioral…