English
Related papers

Related papers: Implicit Bias-Like Patterns in Reasoning Models

200 papers

Social biases inherent in large language models (LLMs) raise significant fairness concerns. Retrieval-Augmented Generation (RAG) architectures, which retrieve external knowledge sources to enhance the generative capabilities of LLMs, remain…

Computation and Language · Computer Science 2026-02-11 Shweta Parihar , Lu Cheng

Large language models (LLMs) solve complex problems by generating multi-step reasoning traces. Yet these traces are typically analyzed from only one of two perspectives: the sequence of tokens across different reasoning steps in the…

Computation and Language · Computer Science 2026-03-25 Ruidi Chang , Jiawei Zhou , Hanjie Chen

Language model (LM) agents are increasingly used as autonomous decision-makers which need to actively gather information to guide their decisions. A crucial cognitive skill for such agents is the efficient exploration and understanding of…

Artificial Intelligence · Computer Science 2025-10-07 Anthony GX-Chen , Dongyan Lin , Mandana Samiei , Doina Precup , Blake A. Richards , Rob Fergus , Kenneth Marino

Recent advances in large language models (LLMs) have popularized the chain-of-thought (CoT) paradigm, in which models produce explicit reasoning steps in natural language. Although this approach improves interpretability and facilitates…

Computation and Language · Computer Science 2025-03-03 José I. Orlicki

Chain-of-thought (CoT) reasoning enhances performance of large language models, but questions remain about whether these reasoning traces faithfully reflect the internal processes of the model. We present the first comprehensive study of…

Computation and Language · Computer Science 2025-11-04 Sriram Balasubramanian , Samyadeep Basu , Soheil Feizi

A prominent challenge for modern language understanding systems is the ability to answer implicit reasoning questions, where the required reasoning steps for answering the question are not mentioned in the text explicitly. In this work, we…

Computation and Language · Computer Science 2022-10-21 Uri Katz , Mor Geva , Jonathan Berant

The handling of probabilities in the form of uncertainty or partial information is an essential task for LLMs in many settings and applications. A common approach to evaluate an LLM's probabilistic reasoning capabilities is to assess its…

Artificial Intelligence · Computer Science 2026-02-12 Manuel Mondal , Ljiljana Dolamic , Gérôme Bovet , Philippe Cudré-Mauroux , Julien Audiffren

Instruction-tuned language models exhibit behavioural fairness in high-stakes decisions while retaining biased associations in their internal representations. However, whether these suppressed representations can affect model outputs - and…

Artificial Intelligence · Computer Science 2026-05-18 Jagdish Tripathy , Marcus Buckmann

As Large Language Models (LLMs) are increasingly adopted as automated judges in benchmarking and reward modeling, ensuring their reliability, efficiency, and robustness has become critical. In this work, we present a systematic comparison…

Artificial Intelligence · Computer Science 2026-05-12 Pratik Jayarao , Himanshu Gupta , Neeraj Varshney , Chaitanya Dwivedi

Binary vulnerability analysis is increasingly performed by LLM-based agents in an iterative, multi-pass manner, with the model as the core decision-maker. However, how such systems organize exploration over hundreds of reasoning steps…

Artificial Intelligence · Computer Science 2026-03-20 Qiang Li , XiangRui Zhang , Haining Wang

Implicit biases in both humans and large language models (LLMs) pose significant societal risks. Dual process theories propose that biases arise primarily from associative System 1 thinking, while deliberative System 2 thinking mitigates…

Computation and Language · Computer Science 2026-04-15 Katherine Abramski , Giulio Rossetti , Massimo Stella

Reward models are central to large language model (LLM) post-training. However, past work has shown that they can reward spurious or undesirable attributes such as length, format, hallucinations, and sycophancy. In this work, we introduce…

Machine Learning · Computer Science 2026-02-18 Atticus Wang , Iván Arcuschin , Arthur Conmy

Recent advancements in Large Reasoning Models (LRMs), such as OpenAI's o1/o3 and DeepSeek-R1, have demonstrated remarkable performance in specialized reasoning tasks through human-like deliberative thinking and long chain-of-thought…

Artificial Intelligence · Computer Science 2025-11-20 Weixiang Zhao , Xingyu Sui , Jiahe Guo , Yulin Hu , Yang Deng , Yanyan Zhao , Xuda Zhi , Yongbo Huang , Hao He , Wanxiang Che , Ting Liu , Bing Qin

While recent safety guardrails effectively suppress overtly biased outputs, subtler forms of social bias emerge during complex logical reasoning tasks that evade current evaluation benchmarks. To fill this gap, we introduce a new evaluation…

Artificial Intelligence · Computer Science 2025-11-11 Fatima Jahara , Mark Dredze , Sharon Levy

Do generative AI models, particularly large language models (LLMs), exhibit systematic behavioral biases in economic and financial decisions? If so, how can these biases be mitigated? Drawing on the cognitive psychology and experimental…

General Economics · Economics 2026-02-11 Pietro Bini , Lin William Cong , Xing Huang , Lawrence J. Jin

Dual process theory posits that human cognition arises via two systems. System 1, which is a quick, emotional, and intuitive process, which is subject to cognitive biases, and System 2, is a slow, onerous, and deliberate process. Prior…

Computation and Language · Computer Science 2025-08-25 Mahammed Kamruzzaman , Gene Louis Kim

Cognitive biases are systematic deviations in thinking that lead to irrational judgments and problematic decision-making, extensively studied across various fields. Recently, large language models (LLMs) have shown advanced understanding…

Computation and Language · Computer Science 2024-10-10 Nuo Chen , Jiqun Liu , Xiaoyu Dong , Qijiong Liu , Tetsuya Sakai , Xiao-Ming Wu

Cognitive biases often shape human decisions. While large language models (LLMs) have been shown to reproduce well-known biases, a more critical question is whether LLMs can predict biases at the individual level and emulate the dynamics of…

Artificial Intelligence · Computer Science 2026-02-27 Stephen Pilli , Vivek Nallur

We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…

Computation and Language · Computer Science 2024-10-31 Rishabh Adiga , Besmira Nushi , Varun Chandrasekaran

Large language models (LLMs) are known to be sensitive to input phrasing, but the mechanisms by which semantic cues shape reasoning remain poorly understood. We investigate this phenomenon in the context of comparative math problems with…

Computation and Language · Computer Science 2025-06-05 Mohammadamin Shafiei , Hamidreza Saffari , Nafise Sadat Moosavi