Related papers: Unveiling Selection Biases: Exploring Order and To…

Large Language Models (LLMs) are increasingly used in tasks such as psychological text analysis and decision-making in automated workflows. However, their reliability remains a concern due to potential biases inherited from their training…

Large language models (LLMs) have achieved state-of-the-art performance on a series of natural language understanding tasks. However, these LLMs might rely on dataset bias and artifacts as shortcuts for prediction. This has significantly…

Talent recruitment is a critical, yet costly process for many industries, with high recruitment costs and long hiring cycles. Existing talent recommendation systems increasingly adopt large language models (LLMs) due to their remarkable…

Large Language Models (LLMs) still struggle with complex logical reasoning. While previous works achieve remarkable improvements, their performance is highly dependent on the correctness of translating natural language (NL) problems into a…

Tabular machine learning problems often require time-consuming and labor-intensive feature engineering. Recent efforts have focused on using large language models (LLMs) to capitalize on their potential domain knowledge. At the same time,…

Large Language Models (LLMs) inherit explicit and implicit biases from their training datasets. Identifying and mitigating biases in LLMs is crucial to ensure fair outputs, as they can perpetuate harmful stereotypes and misinformation. This…

Padding tokens are widely used in large language models (LLMs) to equalize sequence lengths during batched inference. While they should be fully masked, implementation errors can cause them to influence computation, and the extent of this…

This paper examines the role of cognitive biases in the decision-making processes of large language models (LLMs), challenging the conventional goal of eliminating all biases. When properly balanced, we show that certain cognitive biases…

Many applications of large language models (LLMs) require long-context understanding, but models continue to struggle with such tasks. We hypothesize that conventional next-token prediction training could contribute to this, because each…

Tokenization is associated with many poorly understood shortcomings in language models (LMs), yet remains an important component for long sequence scaling purposes. This work studies how tokenization impacts model performance by analyzing…

Data quality plays a critical role in enhancing supervised fine-tuning (SFT) for large language models (LLMs), and token-level data selection has emerged as a promising direction for its fine-grained nature. Despite their strong empirical…

We investigate the choice patterns of Large Language Models (LLMs) in the context of Decisions from Experience tasks that involve repeated choice and learning from feedback, and compare their behavior to human participants. We find that on…

Recently, Large Language Models (LLMs) have demonstrated a superior ability to serve as ranking models. However, concerns have arisen as LLMs will exhibit discriminatory ranking behaviors based on users' sensitive attributes (\eg gender).…

The advent of Large Language Models (LLMs) has revolutionized product recommenders, yet their susceptibility to adversarial manipulation poses critical challenges, particularly in real-world commercial applications. Our approach is the…

User surveys for Quality of Experience (QoE) are a critical source of information. In addition to the common "star rating" used to estimate Mean Opinion Score (MOS), more detailed survey questions (problem tokens) about specific areas…

In English and other languages, multiple adjectives in noun phrases follow intricate ordering patterns. These patterns have been widely studied in linguistics and provide a useful test case for assessing how language models (LMs) acquire…

In this paper we motivate the causal mechanisms behind sample selection induced collider bias (selection collider bias) that can cause Large Language Models (LLMs) to learn unconditional dependence between entities that are unconditionally…

Recent advancements in Large Language Models (LLMs) have made them a popular information-seeking tool among end users. However, the statistical training methods for LLMs have raised concerns about their representation of under-represented…

Agents backed by large language models (LLMs) increasingly rely on external tools drawn from marketplaces where multiple providers offer functionally equivalent options. This raises a critical fairness concern: systematic bias in tool…

In-context learning enables large language models (LLMs) to perform a variety of tasks, including learning to make reward-maximizing choices in simple bandit tasks. Given their potential use as (autonomous) decision-making agents, it is…