English
Related papers

Related papers: Towards Interpreting Language Models: A Case Study…

200 papers

We propose cognitive prompting as a novel approach to guide problem-solving in large language models (LLMs) through structured, human-like cognitive operations, such as goal clarification, decomposition, filtering, abstraction, and pattern…

Computation and Language · Computer Science 2024-12-03 Oliver Kramer , Jill Baumann

Multi-hop inference is necessary for machine learning systems to successfully solve tasks such as Recognising Textual Entailment and Machine Reading. In this work, we demonstrate the effectiveness of adaptive computation for learning the…

Computation and Language · Computer Science 2016-11-17 Mark Neumann , Pontus Stenetorp , Sebastian Riedel

Large language models (LLMs) exhibit remarkable versatility in adopting diverse personas. In this study, we examine how assigning a persona influences a model's reasoning on an objective task. Using activation patching, we take a first step…

Machine Learning · Computer Science 2025-09-23 Ansh Poonia , Maeghal Jain

Multi-Head Attention (MHA) is the core computational primitive underlying modern Large Language Models (LLMs). However, MHA suffers from a fundamental linear scaling limitation: $H$ attention heads produce exactly $H$ independent attention…

As the context window expands, self-attention increasingly dominates the transformer's inference time. Therefore, accelerating attention computation while minimizing performance degradation is essential for the efficient deployment of Large…

Computation and Language · Computer Science 2025-03-14 Eli Sason , Darya Frolova , Boris Nazarov , Felix Goldberd

To address hallucination issues in large language models (LLMs), this paper proposes a method for mitigating prompt-induced hallucinations. Building on a knowledge distillation chain-style model, we introduce a code module to guide…

Computation and Language · Computer Science 2026-01-07 Jinbo Hao , Kai Yang , Qingzhen Su , Yang Chen , Yifan Li , Chao Jiang

Multi-hop reasoning requires aggregating multiple documents to answer a complex question. Existing methods usually decompose the multi-hop question into simpler single-hop questions to solve the problem for illustrating the explainable…

Computation and Language · Computer Science 2022-08-23 Siyuan Wang , Zhongyu Wei , Zhihao Fan , Qi Zhang , Xuanjing Huang

Multi-hop Question Answering (MHQA) adds layers of complexity to question answering, making it more challenging. When Language Models (LMs) are prompted with multiple search results, they are tasked not only with retrieving relevant…

Computation and Language · Computer Science 2025-05-20 Wenyu Huang , Pavlos Vougiouklis , Mirella Lapata , Jeff Z. Pan

Large language models (LLMs) serve as giant information stores, often including personal or copyrighted data, and retraining them from scratch is not a viable option. This has led to the development of various fast, approximate unlearning…

Computation and Language · Computer Science 2024-10-18 Minseok Choi , ChaeHun Park , Dohyun Lee , Jaegul Choo

The reasoning pattern of Large language models (LLMs) remains opaque, and Reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps. This work…

Computation and Language · Computer Science 2025-10-16 Yang Li , Zhichen Dong , Yuhan Sun , Weixun Wang , Shaopan Xiong , Yijia Luo , Jiashun Liu , Han Lu , Jiamang Wang , Wenbo Su , Bo Zheng , Junchi Yan

To bridge the gap between vision and language modalities, Multimodal Large Language Models (MLLMs) usually learn an adapter that converts visual inputs to understandable tokens for Large Language Models (LLMs). However, most adapters…

Computer Vision and Pattern Recognition · Computer Science 2024-05-27 Yue Zhang , Hehe Fan , Yi Yang

Large language models often expose their brittleness in reasoning tasks, especially while executing long chains of reasoning over context. We propose MemReasoner, a new and simple memory-augmented LLM architecture, in which the memory…

Computation and Language · Computer Science 2025-03-12 Payel Das , Ching-Yun Ko , Sihui Dai , Georgios Kollias , Subhajit Chaudhury , Aurelie Lozano

While Pre-trained Language Models (PLMs) internalize a great amount of world knowledge, they have been shown incapable of recalling these knowledge to solve tasks requiring complex & multi-step reasoning. Similar to how humans develop a…

Computation and Language · Computer Science 2022-10-25 Boshi Wang , Xiang Deng , Huan Sun

Large language models (LLMs) often generate plausible yet incorrect answers, posing risks in safety-critical settings such as medicine. Human evaluation is expensive, and LLM-as-judge approaches risk introducing hidden errors. Recent…

Large Language Models (LLMs) have demonstrated amazing capabilities in language generation, text comprehension, and knowledge reasoning. While a single powerful model can already handle multiple tasks, relying on a single perspective can…

Computation and Language · Computer Science 2024-06-12 Zining Qin , Chenhao Wang , Huiling Qin , Weijia Jia

Implicit reasoning is the ability of a language model to solve multi-hop reasoning tasks in a single forward pass, without chain of thought. We investigate this capability using GPT2-style language models trained from scratch on controlled…

Computation and Language · Computer Science 2026-02-05 Yuekun Yao , Yupei Du , Dawei Zhu , Michael Hahn , Alexander Koller

Large Language Models (LLMs), despite their impressive capabilities, often fail to accurately repeat a single word when prompted to, and instead output unrelated text. This unexplained failure mode represents a vulnerability, allowing even…

Machine Learning · Computer Science 2025-03-13 Itay Yona , Ilia Shumailov , Jamie Hayes , Federico Barbero , Yossi Gandelsman

Large language models (LLMs) can solve challenging tasks. However, their inference computation on modern GPUs is highly inefficient due to the increasing number of tokens they must attend to as they generate new ones. To address this…

Computation and Language · Computer Science 2024-04-16 Tian Jin , Wanzin Yazar , Zifei Xu , Sayeh Sharify , Xin Wang

Visual Language Models (VLMs) are powerful generative tools but often produce factually inaccurate outputs due to a lack of robust reasoning capabilities. While extensive research has been conducted on integrating external knowledge for…

Artificial Intelligence · Computer Science 2025-11-26 Shamima Hossain

This paper analyzes the predictions of image captioning models with attention mechanisms beyond visualizing the attention itself. We develop variants of layer-wise relevance propagation (LRP) and gradient-based explanation methods, tailored…

Computer Vision and Pattern Recognition · Computer Science 2021-08-03 Jiamei Sun , Sebastian Lapuschkin , Wojciech Samek , Alexander Binder