Related papers: Implicit Bias-Like Patterns in Reasoning Models
Long-term memory mechanisms enable Large Language Models (LLMs) to maintain continuity and personalization across extended interaction lifecycles, but they also introduce new and underexplored risks related to fairness. In this work, we…
Large Language Models (LLMs) can achieve strong performance on many tasks by producing step-by-step reasoning before giving a final output, often referred to as chain-of-thought reasoning (CoT). It is tempting to interpret these CoT…
Existing memory benchmarks for LLM agents evaluate explicit recall of facts, yet overlook implicit memory where experience becomes automated behavior without conscious retrieval. This gap is critical: effective assistants must automatically…
While advances in fairness and alignment have helped mitigate overt biases exhibited by large language models (LLMs) when explicitly prompted, we hypothesize that these models may still exhibit implicit biases when simulating human…
Chain-of-thought (CoT) prompting has been widely adopted to enhance the reasoning capabilities of large language models (LLMs). However, the effectiveness of CoT reasoning is inconsistent across tasks with different reasoning types. This…
While large language models (LLMs) excel in mathematical and code reasoning, we observe they struggle with social reasoning tasks, exhibiting cognitive confusion, logical inconsistencies, and conflation between objective world states and…
Recent researches indicate that Pre-trained Large Language Models (LLMs) possess cognitive constructs similar to those observed in humans, prompting researchers to investigate the cognitive aspects of LLMs. This paper focuses on explicit…
Vision Language Models (VLMs) are increasingly deployed across downstream tasks, yet their training data often encode social biases that surface in outputs. Unlike humans, who interpret images through contextual and social cues, VLMs…
Large language models (LLMs) have garnered significant attention for their remarkable performance in a continuously expanding set of natural language processing tasks. However, these models have been shown to harbor inherent societal…
Large language models (LLMs) are currently at the forefront of intertwining AI systems with human communication and everyday life. Therefore, it is of great importance to evaluate their emerging abilities. In this study, we show that LLMs…
As Large Language Models (LLMs) continue to evolve, they are increasingly being employed in numerous studies to simulate societies and execute diverse social tasks. However, LLMs are susceptible to societal biases due to their exposure to…
Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making contexts. While prior work has shown that LLMs exhibit cognitive biases behaviorally, whether these biases correspond to identifiable internal…
Large Language Models (LLMs) are increasingly integral to information dissemination and decision-making processes. Given their growing societal influence, understanding potential biases, particularly within the political domain, is crucial…
This research investigates both explicit and implicit social biases exhibited by Vision-Language Models (VLMs). The key distinction between these bias types lies in the level of awareness: explicit bias refers to conscious, intentional…
Large Reasoning Models (LRMs), evolved from standard Large Language Models (LLMs), are increasingly utilized as automated judges because of their explicit reasoning processes. Yet we show that both LRMs and standard LLMs are vulnerable to…
Large Language models (LLMs), such as ChatGPT, have gained popularity in recent years with the advancement of Natural Language Processing (NLP), with use cases spanning many disciplines and daily lives as well. LLMs inherit explicit and…
We investigate the robustness of reasoning models trained for step-by-step problem solving by introducing query-agnostic adversarial triggers - short, irrelevant text that, when appended to math problems, systematically mislead models to…
While reasoning-based large language models excel at complex tasks through an internal, structured thinking process, a concerning phenomenon has emerged that such a thinking process can aggregate social stereotypes, leading to biased…
Do large language models (LLMs) display rational reasoning? LLMs have been shown to contain human biases due to the data they have been trained on; whether this is reflected in rational reasoning remains less clear. In this paper, we answer…
The Implicit Association Test, IAT, is widely used to measure hidden (subconscious) human biases, implicit bias, of many topics: race, gender, age, ethnicity, religion stereotypes. There is a need to understand the reliability of these…