English
Related papers

Related papers: Characterizing Mechanisms for Factual Recall in La…

200 papers

Despite the increasing effectiveness of language models, their reasoning capabilities remain underdeveloped. In particular, causal reasoning through counterfactual question answering is lacking. This work aims to bridge this gap. We first…

Computation and Language · Computer Science 2025-03-18 Alihan Hüyük , Xinnuo Xu , Jacqueline Maasch , Aditya V. Nori , Javier González

Transformer-based pretrained large language models (PLM) such as BERT and GPT have achieved remarkable success in NLP tasks. However, PLMs are prone to encoding stereotypical biases. Although a burgeoning literature has emerged on…

Computation and Language · Computer Science 2024-06-18 Yi Yang , Hanyu Duan , Ahmed Abbasi , John P. Lalor , Kar Yan Tam

To produce accurate predictions, language models (LMs) must balance between generalization and memorization. Yet, little is known about the mechanism by which transformer LMs employ their memorization capacity. When does a model decide to…

Computation and Language · Computer Science 2023-02-14 Adi Haviv , Ido Cohen , Jacob Gidron , Roei Schuster , Yoav Goldberg , Mor Geva

Large language models are able to exploit in-context learning to access external knowledge beyond their training data through retrieval-augmentation. While promising, its inner workings remain unclear. In this work, we shed light on the…

Computation and Language · Computer Science 2025-10-28 Patrick Kahardipraja , Reduan Achtibat , Thomas Wiegand , Wojciech Samek , Sebastian Lapuschkin

Pre-trained Language Models (LMs) exhibit strong zero-shot and in-context learning capabilities; however, their behaviors are often difficult to control. By utilizing Reinforcement Learning from Human Feedback (RLHF), it is possible to…

Computation and Language · Computer Science 2024-05-31 Avelina Asada Hadji-Kyriacou , Ognjen Arandjelovic

Recent work by Chatzi et al. and Ravfogel et al. has developed, for the first time, a method for generating counterfactuals of probabilistic Large Language Models. Such counterfactuals tell us what would - or might - have been the output of…

Artificial Intelligence · Computer Science 2026-04-21 Sander Beckers

Large language models (LLMs) such as GPT, Gemini, and Claude often appear adept at solving classic logic puzzles--but how much genuine reasoning underlies their answers? Recent evidence suggests that these models frequently rely on…

Computation and Language · Computer Science 2025-10-15 Souradeep Mukhopadhyay , Rishabh Baral , Nimeesh Mahajan , Samhitha Harish , Aswin RRV , Mihir Parmar , Mutsumi Nakamura , Chitta Baral

LLMs can be unpredictable, as even slight alterations to the prompt can cause the output to change in unexpected ways. Thus, the ability of models to accurately explain their behavior is critical, especially in high-stakes settings. One…

Computation and Language · Computer Science 2025-11-26 Marvin Limpijankit , Yanda Chen , Melanie Subbiah , Nicholas Deas , Kathleen McKeown

Recently, there has been a trend to investigate the factual knowledge captured by Pre-trained Language Models (PLMs). Many works show the PLMs' ability to fill in the missing factual words in cloze-style prompts such as "Dante was born in…

Computation and Language · Computer Science 2022-04-01 Shaobo Li , Xiaoguang Li , Lifeng Shang , Zhenhua Dong , Chengjie Sun , Bingquan Liu , Zhenzhou Ji , Xin Jiang , Qun Liu

Previous works show that Pre-trained Language Models (PLMs) can capture factual knowledge. However, some analyses reveal that PLMs fail to perform it robustly, e.g., being sensitive to the changes of prompts when extracting factual…

Computation and Language · Computer Science 2022-10-21 Shaobo Li , Xiaoguang Li , Lifeng Shang , Chengjie Sun , Bingquan Liu , Zhenzhou Ji , Xin Jiang , Qun Liu

Pre-training on large corpora of text enables the language models to acquire a vast amount of factual and commonsense knowledge which allows them to achieve remarkable performance on a variety of language understanding tasks. They typically…

Computation and Language · Computer Science 2023-05-23 Neeraj Varshney , Mihir Parmar , Nisarg Patel , Divij Handa , Sayantan Sarkar , Man Luo , Chitta Baral

As Large Language Models (LLMs) continue to evolve, more are being designed to handle long-context inputs. Despite this advancement, most of them still face challenges in accurately handling long-context tasks, often showing the "lost in…

Computation and Language · Computer Science 2024-12-13 Yijiong Yu , Yongfeng Huang , Zhixiao Qi , Zhe Zhou

Pre-trained Language Models (PLMs) have shown impressive results in various Natural Language Generation (NLG) tasks, such as powering chatbots and generating stories. However, an ethical concern arises due to their potential to produce…

Computation and Language · Computer Science 2024-06-04 Kaixin Lan , Tao Fang , Derek F. Wong , Yabo Xu , Lidia S. Chao , Cecilia G. Zhao

Memorization, or the tendency of large language models (LLMs) to output entire sequences from their training data verbatim, is a key concern for safely deploying language models. In particular, it is vital to minimize a model's memorization…

Computation and Language · Computer Science 2023-06-02 Stella Biderman , USVSN Sai Prashanth , Lintang Sutawika , Hailey Schoelkopf , Quentin Anthony , Shivanshu Purohit , Edward Raff

Sample efficiency is a crucial property of language models with practical implications for training efficiency. In real-world text, information follows a long-tailed distribution. Yet, we expect models to learn and recall frequent and…

Computation and Language · Computer Science 2025-06-23 Daniel Christoph , Max Ploner , Patrick Haller , Alan Akbik

The training data in large language models is key to their success, but it also presents privacy and security risks, as it may contain sensitive information. Detecting pre-training data is crucial for mitigating these concerns. Existing…

Computation and Language · Computer Science 2025-01-16 Cheng Wang , Yiwei Wang , Bryan Hooi , Yujun Cai , Nanyun Peng , Kai-Wei Chang

In recent years, several Speech Language Models (SLMs) that represent speech and written text jointly have been presented. The question then emerges about how model-internal mechanisms are similar and different when operating in the two…

Computation and Language · Computer Science 2026-05-22 Luca Modica , Filip Landin , Mehrdad Farahani , Livia Qian , Gabriel Skantze , Richard Johansson

Real-world conversations are rich with pragmatic elements, such as entity mentions, references, and implicatures. Understanding such nuances is a requirement for successful natural communication, and often requires building a local world…

Artificial Intelligence · Computer Science 2025-11-18 Sachin Vashistha , Aryan Bibhuti , Atharva Naik , Martin Tutek , Somak Aditya

Petroni et al. (2019) demonstrated that it is possible to retrieve world facts from a pre-trained language model by expressing them as cloze-style prompts and interpret the model's prediction accuracy as a lower bound on the amount of…

Computation and Language · Computer Science 2021-12-15 Zexuan Zhong , Dan Friedman , Danqi Chen

Large language models store biomedical facts with uneven strength after pretraining: some facts are present in the weights but are not reliably accessible under deterministic decoding (latent knowledge), while others are scarcely…

Computation and Language · Computer Science 2026-01-27 Daniel B. Hier , Tayo Obafemi-Ajayi