English
Related papers

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

200 papers

In a multilingual neural machine translation model that fully shares parameters across all languages, an artificial language token is usually used to guide translation into the desired target language. However, recent studies show that…

Computation and Language · Computer Science 2022-09-07 Renren Jin , Deyi Xiong

Recent work has shown that language models (LMs) have strong multi-step (i.e., procedural) reasoning capabilities. However, it is unclear whether LMs perform these tasks by cheating with answers memorized from pretraining corpus, or, via a…

Computation and Language · Computer Science 2023-10-24 Yifan Hou , Jiaoda Li , Yu Fei , Alessandro Stolfo , Wangchunshu Zhou , Guangtao Zeng , Antoine Bosselut , Mrinmaya Sachan

Advances in language modeling have led to the development of deep attention-based models that are performant across a wide variety of natural language processing (NLP) problems. These language models are typified by a pre-training process…

Human-Computer Interaction · Computer Science 2020-09-16 Joseph F DeRose , Jiayao Wang , Matthew Berger

``Socrates is human. All humans are mortal. Therefore, Socrates is mortal.'' This form of argument illustrates a typical pattern of two-hop reasoning. Formally, two-hop reasoning refers to the process of inferring a conclusion by making two…

Computation and Language · Computer Science 2025-05-29 Tianyu Guo , Hanlin Zhu , Ruiqi Zhang , Jiantao Jiao , Song Mei , Michael I. Jordan , Stuart Russell

Two of the central factors believed to underpin human sentence processing difficulty are expectations and retrieval from working memory. A recent attempt to create a unified cognitive model integrating these two factors relied on the…

Computation and Language · Computer Science 2023-10-26 William Timkey , Tal Linzen

Achieving human-level performance on some of the Machine Reading Comprehension (MRC) datasets is no longer challenging with the help of powerful Pre-trained Language Models (PLMs). However, the internal mechanism of these artifacts remains…

Computation and Language · Computer Science 2024-10-29 Yiming Cui , Wei-Nan Zhang , Wanxiang Che , Ting Liu , Zhigang Chen , Shijin Wang

In recent years, the use of large language models (LLMs) has significantly increased, and these models have demonstrated remarkable performance in a variety of general language tasks. However, the evaluation of their performance in…

Computation and Language · Computer Science 2025-01-14 Iman Barati , Arash Ghafouri , Behrouz Minaei-Bidgoli

In large language model-based agents, memory serves as a critical capability for achieving personalization by storing and utilizing users' information. Although some previous studies have adopted memory to implement user personalization,…

Artificial Intelligence · Computer Science 2025-08-20 Zeyu Zhang , Yang Zhang , Haoran Tan , Rui Li , Xu Chen

Chain-of-thought (CoT) reasoning has become the standard paradigm for enabling Large Language Models (LLMs) to solve complex problems. However, recent studies reveal a sharp performance drop in reasoning hop generalization scenarios, where…

Computation and Language · Computer Science 2026-05-04 Zhaoyi Li , Jiatong Li , Gangwei Jiang , Linqi Song , Defu Lian , Ying Wei

Multi-hop questions still stump large language models (LLMs), which struggle to link information across multiple reasoning steps. We introduce Auto-Patch, a novel method that dynamically patches hidden states during inference to enhance…

Computation and Language · Computer Science 2025-06-03 Aviv Jan , Dean Tahory , Omer Talmi , Omar Abo Mokh

Although it is known that transformer language models (LMs) pass features from early layers to later layers, it is not well understood how this information is represented and routed by the model. We analyze a mechanism used in two LMs to…

Computation and Language · Computer Science 2025-05-12 Jack Merullo , Carsten Eickhoff , Ellie Pavlick

Recent developments in Language Models (LMs) have shown their effectiveness in NLP tasks, particularly in knowledge-intensive tasks. However, the mechanisms underlying knowledge storage and memory access within their parameters remain…

Computation and Language · Computer Science 2024-07-23 Tongyao Zhu , Qian Liu , Liang Pang , Zhengbao Jiang , Min-Yen Kan , Min Lin

Large language models can use chain-of-thought (CoT) to externalize reasoning, potentially enabling oversight of capable LLM agents. Prior work has shown that models struggle at two-hop question-answering without CoT. This capability is so…

Computation and Language · Computer Science 2025-11-25 Mikita Balesni , Tomek Korbak , Owain Evans

We present Prompt Cache, an approach for accelerating inference for large language models (LLM) by reusing attention states across different LLM prompts. Many input prompts have overlapping text segments, such as system messages, prompt…

Computation and Language · Computer Science 2024-04-26 In Gim , Guojun Chen , Seung-seob Lee , Nikhil Sarda , Anurag Khandelwal , Lin Zhong

Prompt learning has emerged as an efficient alternative for fine-tuning foundational models, such as CLIP, for various downstream tasks. However, there is no work that provides a comprehensive explanation for the working mechanism of the…

Computer Vision and Pattern Recognition · Computer Science 2024-03-13 Shuailei Ma , Chen-Wei Xie , Ying Wei , Siyang Sun , Jiaqi Fan , Xiaoyi Bao , Yuxin Guo , Yun Zheng

Language models (LMs) behave more like humans when their cognitive resources are restricted, particularly in predicting sentence processing costs such as reading times. However, it remains unclear whether such constraints similarly affect…

Computation and Language · Computer Science 2026-04-30 Rei Emura , Saku Sugawara

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

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) perform well on multi-hop reasoning, yet how they internally compose multiple facts remains unclear. Recent work proposes \emph{hop-aligned circuit hypothesis}, suggesting that bridge entities are computed…

Computation and Language · Computer Science 2026-01-08 Xukai Liu , Ye Liu , Jipeng Zhang , Yanghai Zhang , Kai Zhang , Qi Liu

A cache-inspired approach is proposed for neural language models (LMs) to improve long-range dependency and better predict rare words from long contexts. This approach is a simpler alternative to attention-based pointer mechanism that…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-30 Ke Li , Daniel Povey , Sanjeev Khudanpur