English
Related papers

Related papers: Mathematical Reasoning via Intervention-Based Time…

200 papers

This study sheds light on the imperative need to bolster safety and privacy measures in large language models (LLMs), such as GPT-4 and LLaMA-2, by identifying and mitigating their vulnerabilities through explainable analysis of prompt…

Cryptography and Security · Computer Science 2024-07-18 Dong Shu , Mingyu Jin , Tianle Chen , Chong Zhang , Yongfeng Zhang

This paper introduces a causal attribution model to enhance the interpretability of large language models (LLMs) and improve their causal reasoning abilities via precise fine-tuning. Despite LLMs' proficiency in diverse tasks, their…

Artificial Intelligence · Computer Science 2026-05-22 Hengrui Cai , Shengjie Liu , Rui Song

Recent studies have demonstrated that Large Language Models (LLMs) have strong mathematical reasoning abilities but rely on hundreds of billions of parameters. To tackle the challenge of poor reasoning in Small Language Models (SLMs),…

Computation and Language · Computer Science 2025-08-19 Xinhe Li , Jiajun Liu , Peng Wang

Causal discovery witnessed significant progress over the past decades. In particular, many recent causal discovery methods make use of independent, non-Gaussian noise to achieve identifiability of the causal models. Existence of hidden…

Machine Learning · Statistics 2019-09-06 Chenwei Ding , Mingming Gong , Kun Zhang , Dacheng Tao

Current Reinforcement Learning (RL) methods often suffer from sample-inefficiency, resulting from blind exploration strategies that neglect causal relationships among states, actions, and rewards. Although recent causal approaches aim to…

Artificial Intelligence · Computer Science 2025-02-17 Hongye Cao , Fan Feng , Tianpei Yang , Jing Huo , Yang Gao

Causal probing methods aim to test and control how internal representations influence the behavior of generative models. In causal probing, an intervention modifies hidden states so that a property takes on a different value. Most existing…

Artificial Intelligence · Computer Science 2026-05-11 Sadegh Khorasani , Saber Salehkaleybar , Negar Kiyavash , Matthias Grossglauser

In reasoning tasks, even a minor error can cascade into inaccurate results, leading to suboptimal performance of large language models in such domains. Earlier fine-tuning approaches sought to mitigate this by leveraging more precise…

Computation and Language · Computer Science 2024-07-12 Changyu Chen , Xiting Wang , Ting-En Lin , Ang Lv , Yuchuan Wu , Xin Gao , Ji-Rong Wen , Rui Yan , Yongbin Li

The causal capabilities of large language models (LLMs) are a matter of significant debate, with critical implications for the use of LLMs in societally impactful domains such as medicine, science, law, and policy. We conduct a "behavorial"…

Artificial Intelligence · Computer Science 2024-08-21 Emre Kıcıman , Robert Ness , Amit Sharma , Chenhao Tan

Recent advances in Vision-Language Models (VLMs) have demonstrated impressive capabilities in perception and reasoning. However, the ability to perform causal inference -- a core aspect of human cognition -- remains underexplored,…

Computation and Language · Computer Science 2025-08-14 Keummin Ka , Junhyeong Park , Jaehyun Jeon , Youngjae Yu

Knowledge-based question answering (KBQA) is a key task in NLP research, and also an approach to access the web data and knowledge, which requires exploiting knowledge graphs (KGs) for reasoning. In the literature, one promising solution…

Computation and Language · Computer Science 2024-03-18 Xin Lin , Tianhuang Su , Zhenya Huang , Shangzi Xue , Haifeng Liu , Enhong Chen

Large Language Models (LLMs) are increasingly used in tasks requiring interpretive and inferential accuracy. In this paper, we introduce ExpliCa, a new dataset for evaluating LLMs in explicit causal reasoning. ExpliCa uniquely integrates…

Computation and Language · Computer Science 2026-02-10 Martina Miliani , Serena Auriemma , Alessandro Bondielli , Emmanuele Chersoni , Lucia Passaro , Irene Sucameli , Alessandro Lenci

Hallucinations (i.e., generating plausible but inaccurate content) and laziness (i.e. excessive refusals or defaulting to "I don't know") persist as major challenges in LLM reasoning. Current efforts to reduce hallucinations primarily focus…

Machine Learning · Computer Science 2025-03-21 Zirui Zhao , Hanze Dong , Amrita Saha , Caiming Xiong , Doyen Sahoo

Continuing advances in Large Language Models (LLMs) in artificial intelligence offer important capacities in intuitively accessing and using medical knowledge in many contexts, including education and training as well as assessment and…

Computation and Language · Computer Science 2024-08-01 Roma Shusterman , Allison C. Waters , Shannon O`Neill , Phan Luu , Don M. Tucker

The ability to perform causal reasoning is widely considered a core feature of intelligence. In this work, we investigate whether large language models (LLMs) can coherently reason about causality. Much of the existing work in natural…

Legal Judgment Prediction (LJP), aiming to predict a judgment based on fact descriptions according to rule of law, serves as legal assistance to mitigate the great work burden of limited legal practitioners. Most existing methods apply…

Computation and Language · Computer Science 2023-04-19 Haotian Chen , Lingwei Zhang , Yiran Liu , Fanchao Chen , Yang Yu

Deep learning models trained on extensive Electronic Health Records (EHR) data have achieved high accuracy in diagnosis prediction, offering the potential to assist clinicians in decision-making and treatment planning. However, these models…

Artificial Intelligence · Computer Science 2025-09-30 Xiaoxue Han , Pengfei Hu , Jun-En Ding , Chang Lu , Feng Liu , Yue Ning

Contemporary machine learning optimizes for predictive accuracy, yet systems that achieve state of the art performance remain causally opaque: their internal representations provide no principled handle for intervention. We can retrain such…

Artificial Intelligence · Computer Science 2025-10-28 Marcus Thomas

Numerical reasoning is vital for natural language processing models to understand and process numerical information in real-world scenarios. Most current methods first generate the Intermediate Meaning Representations (IMRs) of questions…

Computation and Language · Computer Science 2023-08-22 Dingzirui Wang , Longxu Dou , Wenbin Zhang , Junyu Zeng , Wanxiang Che

Despite the advancements in large language models (LLMs) for mathematical reasoning, solving competition-level math problems remains a significant challenge, especially for open-source LLMs without external tools. We introduce the MMIQC…

Computation and Language · Computer Science 2024-12-17 Haoxiong Liu , Yifan Zhang , Yifan Luo , Andrew Chi-Chih Yao

In the realm of embodied artificial intelligence, the reasoning capabilities of Large Language Models (LLMs) play a pivotal role. Although there are effective methods like program-of-thought prompting for LLMs which uses programming…

Computation and Language · Computer Science 2023-12-19 Zhen Bi , Ningyu Zhang , Yinuo Jiang , Shumin Deng , Guozhou Zheng , Huajun Chen