English
Related papers

Related papers: Composition Collapse: Stable Factual Knowledge Doe…

200 papers

This paper presents ReasonFormer, a unified reasoning framework for mirroring the modular and compositional reasoning process of humans in complex decision-making. Inspired by dual-process theory in cognitive science, the representation…

Computation and Language · Computer Science 2022-12-08 Wanjun Zhong , Tingting Ma , Jiahai Wang , Jian Yin , Tiejun Zhao , Chin-Yew Lin , Nan Duan

Language interpretation is a compositional process, in which the meaning of more complex linguistic structures is inferred from the meaning of their parts. Large language models possess remarkable language interpretation capabilities and…

Artificial Intelligence · Computer Science 2025-10-31 David Maria Schmidt , Raoul Schubert , Philipp Cimiano

Code has become a standard component of modern foundation language model (LM) training, yet its role beyond programming remains unclear. We revisit the claim that code improves reasoning through controlled pretraining experiments on a…

Artificial Intelligence · Computer Science 2026-05-20 Yuze Zhao , Junpeng Fang , Lu Yu , Zhenya Huang , Kai Zhang , Qing Cui , Qi Liu , Jun Zhou , Enhong Chen

LLM-based formal proof assistants (e.g., in Lean) hold great promise for automating mathematical discovery. But beyond syntactic correctness, do these systems truly understand mathematical structure as humans do? We investigate this…

Artificial Intelligence · Computer Science 2025-10-21 Haoyu Zhao , Yihan Geng , Shange Tang , Yong Lin , Bohan Lyu , Hongzhou Lin , Chi Jin , Sanjeev Arora

In this paper, we address the challenging task of multimodal mathematical reasoning by incorporating the ability of "slow thinking" into multimodal large language models (MLLMs). Our core idea is that different levels of reasoning abilities…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Kun Xiang , Zhili Liu , Zihao Jiang , Yunshuang Nie , Kaixin Cai , Yiyang Yin , Runhui Huang , Haoxiang Fan , Hanhui Li , Weiran Huang , Yihan Zeng , Yu-Jie Yuan , Jianhua Han , Lanqing Hong , Hang Xu , Xiaodan Liang

Knowledge graphs are essential for numerous downstream natural language processing applications, but are typically incomplete with many facts missing. This results in research efforts on multi-hop reasoning task, which can be formulated as…

Artificial Intelligence · Computer Science 2021-09-03 Yao Zhang , Hongru Liang , Adam Jatowt , Wenqiang Lei , Xin Wei , Ning Jiang , Zhenglu Yang

Recent Long-Context Language Models (LCLMs) can process hundreds of thousands of tokens in a single prompt, enabling new opportunities for knowledge-intensive multi-hop reasoning by integrating large sets of retrieved documents or, in some…

Computation and Language · Computer Science 2026-04-29 Soyeong Jeong , Taehee Jung , Sung Ju Hwang , Joo-Kyung Kim , Dongyeop Kang

Retrieval-augmented large language models, when optimized with outcome-level rewards, can achieve strong answer accuracy on multi-hop questions. However, under noisy retrieval, models frequently suffer from "right-answer-wrong-reason…

Computation and Language · Computer Science 2026-03-17 Yu Liu , Wenxiao Zhang , Diandian Guo , Cong Cao , Fangfang Yuan , Qiang Sun , Yanbing Liu , Jin B. Hong , Zhiyuan Ma

Multi-hop reasoning approaches over knowledge graphs infer a missing relationship between entities with a multi-hop rule, which corresponds to a chain of relationships. We extend existing works to consider a generalized form of multi-hop…

Computation and Language · Computer Science 2020-10-06 Lu Zhang , Mo Yu , Tian Gao , Yue Yu

Learning structural information from observational data is central to producing new knowledge outside the training corpus. This holds for mechanistic understanding in scientific discovery as well as flexible test-time compositional…

Computation and Language · Computer Science 2026-01-27 Michelle Chao Chen , Moritz Miller , Bernhard Schölkopf , Siyuan Guo

Reasoning models are evaluated on single-turn benchmarks but deployed in multi-turn dialogue, where users push back on correct answers. Under sustained adversarial pressure we find a previously undocumented failure mode: the…

Artificial Intelligence · Computer Science 2026-05-29 Yubo Li , Ramayya Krishnan , Rema Padman

Transformers have achieved great success in numerous NLP tasks but continue to exhibit notable gaps in multi-step factual reasoning, especially when real-world knowledge is sparse. Recent advances in grokking have demonstrated that neural…

Computation and Language · Computer Science 2025-05-08 Roman Abramov , Felix Steinbauer , Gjergji Kasneci

Multi-hop question answering (QA) is widely used to evaluate the reasoning capabilities of large language models, yet most benchmarks focus on final answer correctness and overlook intermediate reasoning, especially in long multimodal…

Computation and Language · Computer Science 2026-03-10 Biao Xiang , Soyeon Caren Han , Yihao Ding

Multimodal reasoning models often produce fluent answers supported by seemingly coherent rationales. Existing benchmarks evaluate only final-answer correctness. They do not support atomic visual entailment verification of intermediate…

Artificial Intelligence · Computer Science 2026-03-25 Saleem Ahmed , Srirangaraj Setlur , Venu Govindaraju

A fundamental characteristic of audio is its compositional nature. Audio-language models (ALMs) trained using a contrastive approach (e.g., CLAP) that learns a shared representation between audio and language modalities have improved…

People can acquire knowledge in an unsupervised manner by reading, and compose the knowledge to make novel combinations. In this paper, we investigate whether pretrained language models can perform compositional generalization in a…

Computation and Language · Computer Science 2022-10-21 Xiao Liu , Yansong Feng , Jizhi Tang , Chengang Hu , Dongyan Zhao

Evaluations of unlearning on reasoning models sometimes show a bypass pattern. The answer side looks unlearned, but the model's own thinking trace keeps emitting the forgotten content, and the gap is taken as evidence that the weights still…

Machine Learning · Computer Science 2026-05-20 Yanhang Li , Zhichao Fan , Zexin Zhuang

Vision-Language Models (VLMs) have achieved strong performance on implicit and explicit visual grounding and related tasks. However, such abilities are generally tested on simple, single-object phrases. We find that grounding performance…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Jiayun Luo , Mir Rayat Imtiaz Hossain , Pritam Sarkar , Boyang Li , Leonid Sigal

In this paper, we propose a comprehensive benchmark to investigate models' logical reasoning capabilities in complex real-life scenarios. Current explanation datasets often employ synthetic data with simple reasoning structures. Therefore,…

Artificial Intelligence · Computer Science 2022-10-25 Yinya Huang , Hongming Zhang , Ruixin Hong , Xiaodan Liang , Changshui Zhang , Dong Yu

While Large Language Models (LLMs) excel in question-answering (QA) tasks, their real reasoning abilities on multiple evidence retrieval and integration on Multi-hop QA tasks remain less explored. Firstly, LLMs sometimes generate answers…

Computation and Language · Computer Science 2024-10-16 Jian Wu , Linyi Yang , Zhen Wang , Manabu Okumura , Yue Zhang
‹ Prev 1 8 9 10 Next ›