English
Related papers

Related papers: Chunky Post-Training: Data Driven Failures of Gene…

200 papers

Recent progress in large language models has led to the emergence of reasoning models, which have shown strong performance on complex tasks through specialized fine-tuning procedures. While these methods reliably improve pass@1 accuracy,…

Machine Learning · Computer Science 2026-05-19 Ngoc-Hieu Nguyen , Parshin Shojaee , Phuc Minh Nguyen , Nan Zhang , Chandan K Reddy , Khoa D Doan , Rui Zhang

Having been trained on massive pretraining data, large language models have shown excellent performance on many knowledge-intensive tasks. However, pretraining data tends to contain misleading and even conflicting information, and it is…

Computation and Language · Computer Science 2024-10-08 Jiahuan Li , Yiqing Cao , Shujian Huang , Jiajun Chen

Language models (LMs) often exhibit undesirable text generation behaviors, including generating false, toxic, or irrelevant outputs. Reinforcement learning from human feedback (RLHF) - where human preference judgments on LM outputs are…

Computation and Language · Computer Science 2023-10-31 Zeqiu Wu , Yushi Hu , Weijia Shi , Nouha Dziri , Alane Suhr , Prithviraj Ammanabrolu , Noah A. Smith , Mari Ostendorf , Hannaneh Hajishirzi

While many have shown how Large Language Models (LLMs) can be applied to a diverse set of tasks, the critical issues of data contamination and memorization are often glossed over. In this work, we address this concern for tabular data.…

Machine Learning · Computer Science 2024-12-05 Sebastian Bordt , Harsha Nori , Vanessa Rodrigues , Besmira Nushi , Rich Caruana

As synthetic content increasingly infiltrates the web, generative AI models may be retrained on their own outputs: a process termed "autophagy". This leads to model collapse: a progressive loss of performance and diversity across…

Computation and Language · Computer Science 2025-09-03 Daniele Gambetta , Gizem Gezici , Fosca Giannotti , Dino Pedreschi , Alistair Knott , Luca Pappalardo

Large language models (LLMs) have achieved remarkable success in machine translation, demonstrating impressive performance across diverse languages. However, translationese, characterized by overly literal and unnatural translations,…

Computation and Language · Computer Science 2025-03-07 Yafu Li , Ronghao Zhang , Zhilin Wang , Huajian Zhang , Leyang Cui , Yongjing Yin , Tong Xiao , Yue Zhang

Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while maintaining its performance on standard tasks. While…

Machine Learning · Computer Science 2026-03-03 Yiwei Chen , Soumyadeep Pal , Yimeng Zhang , Qing Qu , Sijia Liu

Large Language Models (LLMs) have demonstrated great capabilities in natural language understanding and generation, largely attributed to the intricate alignment process using human feedback. While alignment has become an essential training…

Computation and Language · Computer Science 2024-09-04 Bocheng Chen , Hanqing Guo , Guangjing Wang , Yuanda Wang , Qiben Yan

LLMs often exhibit Aha moments such as self-correction after tokens like "Wait," yet the underlying mechanism remains unclear. Standard LLMs collapse mainly through silent divergence, where trajectories drift from the correct answer yet…

Artificial Intelligence · Computer Science 2026-05-27 Jeonghye Kim , Xufang Luo , Minbeom Kim , Sangmook Lee , Dongsheng Li , Yuqing Yang

Large language models (LLMs) exhibit failure modes on seemingly trivial tasks. We propose a formalisation of LLM interaction using a deterministic multi-tape Turing machine, where each tape represents a distinct component: input characters,…

Computation and Language · Computer Science 2026-02-20 Magnus Boman

While Diffusion Language Models (DLMs) are theoretically well-suited for iterative refinement due to their non-causal structure, they often fail to reliably revise incorrect tokens in practice. The key challenge lies in the model's…

Machine Learning · Computer Science 2026-01-30 Shuibai Zhang , Fred Zhangzhi Peng , Yiheng Zhang , Jin Pan , Grigorios G. Chrysos

We propose a novel training regime termed counterfactual training that leverages counterfactual explanations to increase the explanatory capacity of models. Counterfactual explanations have emerged as a popular post-hoc explanation method…

Machine Learning · Computer Science 2026-01-23 Patrick Altmeyer , Aleksander Buszydlik , Arie van Deursen , Cynthia C. S. Liem

Existing training approaches for large language models learn a single set of parameters, based on large volumes of data, which is typically heterogeneous, conflicting and often outright contradictory. As a result, the model is forced to…

Machine Learning · Statistics 2026-05-28 Paula Cordero-Encinar , Georgy Tyukin , Andrew B. Duncan

The success of Large Language Models (LLMs) relies heavily on the huge amount of pre-training data learned in the pre-training phase. The opacity of the pre-training process and the training data causes the results of many benchmark tests…

Computation and Language · Computer Science 2025-03-03 Shiwen Ni , Xiangtao Kong , Chengming Li , Xiping Hu , Ruifeng Xu , Jia Zhu , Min Yang

By pretraining on trillions of tokens, an LLM gains the capability of text generation. However, to enhance its utility and reduce potential harm, SFT and alignment are applied sequentially to the pretrained model. Because SFT and alignment…

Computation and Language · Computer Science 2026-05-11 Zhichao Wang , Bin Bi , Zixu Zhu , Xiangbo Mao , Jun Wang , Shiyu Wang , Cheng Wang , Dong Nie , Lingzi Hong

Despite warnings that LLMs can make mistakes, users often develop inappropriate trust and accept incorrect answers without critical evaluation. Uncertainty quantification (UQ), displaying LLMs' confidence, has emerged as a promising…

Human-Computer Interaction · Computer Science 2026-05-28 Mauricio Villavicencio , Sitong Pan , Qianwen Wang

Large Language Models (LLMs) that can express interpretable and calibrated uncertainty are crucial in high-stakes domains. While methods to compute uncertainty post-hoc exist, they are often sampling-based and therefore computationally…

Machine Learning · Computer Science 2026-03-09 Azza Jenane , Nassim Walha , Lukas Kuhn , Florian Buettner

Frontier AI systems are making transformative impacts across society, but such benefits are not without costs: models trained on web-scale datasets containing personal and private data raise profound concerns about data privacy and…

Computer Vision and Pattern Recognition · Computer Science 2024-07-26 Sunny Duan , Mikail Khona , Abhiram Iyer , Rylan Schaeffer , Ila R Fiete

The training dynamics of deep neural networks often defy expectations, even as these models form the foundation of modern machine learning. Two prominent examples are grokking, where test performance improves abruptly long after the…

Machine Learning · Computer Science 2026-01-28 Keitaro Sakamoto , Issei Sato

Large language models (LLMs) may memorize sensitive or copyrighted content, raising privacy and legal concerns. Due to the high cost of retraining from scratch, researchers attempt to employ machine unlearning to remove specific content…

Computation and Language · Computer Science 2025-08-12 Xiaojian Yuan , Tianyu Pang , Chao Du , Kejiang Chen , Weiming Zhang , Min Lin