English
Related papers

Related papers: Discovering Latent Knowledge in Language Models Wi…

200 papers

Intrinsic self-correct was a method that instructed large language models (LLMs) to verify and correct their responses without external feedback. Unfortunately, the study concluded that the LLMs could not self-correct reasoning yet. We find…

Computation and Language · Computer Science 2024-10-04 Zhenyu Wu , Qingkai Zeng , Zhihan Zhang , Zhaoxuan Tan , Chao Shen , Meng Jiang

Recent Vision-based Large Language Models~(VisionLLMs) for autonomous driving have seen rapid advancements. However, such promotion is extremely dependent on large-scale high-quality annotated data, which is costly and labor-intensive. To…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Chaoqun Wang , Jie Yang , Xiaobin Hong , Ruimao Zhang

Language models are trained on large volumes of text, and as a result their parameters might contain a significant body of factual knowledge. Any downstream task performed by these models implicitly builds on these facts, and thus it is…

Computation and Language · Computer Science 2023-01-31 Roi Cohen , Mor Geva , Jonathan Berant , Amir Globerson

Subword modeling for zero-resource languages aims to learn low-level representations of speech audio without using transcriptions or other resources from the target language (such as text corpora or pronunciation dictionaries). A good…

Audio and Speech Processing · Electrical Eng. & Systems 2020-04-20 Enno Hermann , Herman Kamper , Sharon Goldwater

We present a deep generative model for learning to predict classes not seen at training time. Unlike most existing methods for this problem, that represent each class as a point (via a semantic embedding), we represent each seen/unseen…

Machine Learning · Computer Science 2017-11-21 Wenlin Wang , Yunchen Pu , Vinay Kumar Verma , Kai Fan , Yizhe Zhang , Changyou Chen , Piyush Rai , Lawrence Carin

Large language models (LLMs) have shown remarkable advances in language generation and understanding but are also prone to exhibiting harmful social biases. While recognition of these behaviors has generated an abundance of bias mitigation…

We posit that large language models (LLMs) should be capable of expressing their intrinsic uncertainty in natural language. For example, if the LLM is equally likely to output two contradicting answers to the same question, then its…

Computation and Language · Computer Science 2024-09-27 Gal Yona , Roee Aharoni , Mor Geva

Large language models memorize parts of their training data. Memorizing short snippets and facts is required to answer questions about the world and to be fluent in any language. But models have also been shown to reproduce long verbatim…

Computation and Language · Computer Science 2024-11-18 Michael Aerni , Javier Rando , Edoardo Debenedetti , Nicholas Carlini , Daphne Ippolito , Florian Tramèr

Alignment of large language models (LLMs) with human values and preferences, often achieved through fine-tuning based on human feedback, is essential for ensuring safe and responsible AI behaviors. However, the process typically requires…

Computation and Language · Computer Science 2025-02-10 Runjin Chen , Gabriel Jacob Perin , Xuxi Chen , Xilun Chen , Yan Han , Nina S. T. Hirata , Junyuan Hong , Bhavya Kailkhura

Language Models (LMs) can perform new tasks by adapting to a few in-context examples. For humans, explanations that connect examples to task principles can improve learning. We therefore investigate whether explanations of few-shot examples…

Large language models (LLMs) are increasingly used in decision-making contexts, but when they present answers without signaling low confidence, users may unknowingly act on erroneous outputs. Prior work shows that LLMs maintain internal…

Computation and Language · Computer Science 2025-10-23 Mark Steyvers , Catarina Belem , Padhraic Smyth

Large language models inevitably retain sensitive information, defined as inputs that may induce harmful generations, due to training on massive web corpora, raising concerns for privacy and safety. Existing machine unlearning methods…

Machine Learning · Computer Science 2026-05-21 Yujie Lin , Chengyi Yang , Zhishang Xiang , Yiping Song , Jinsong Su

Numerical reasoning over natural language has been a long-standing goal for the research community. However, cutting-edge language models have proven difficult to reliably generalize to a broad range of numbers, although they have shown…

Computation and Language · Computer Science 2022-10-12 Fan Zhou , Haoyu Dong , Qian Liu , Zhoujun Cheng , Shi Han , Dongmei Zhang

While Large Multimodal Models (LMMs) have made significant progress, they remain largely text-centric, relying on language as their core reasoning modality. As a result, they are limited in their ability to handle reasoning tasks that are…

Computer Vision and Pattern Recognition · Computer Science 2025-12-25 Kelvin Li , Chuyi Shang , Leonid Karlinsky , Rogerio Feris , Trevor Darrell , Roei Herzig

There has been recent interest in whether large language models (LLMs) can introspect about their own internal states. Such abilities would make LLMs more interpretable, and also validate the use of standard introspective methods in…

Computation and Language · Computer Science 2025-09-25 Siyuan Song , Jennifer Hu , Kyle Mahowald

Supervised training of neural models to duplicate question detection in community Question Answering (cQA) requires large amounts of labeled question pairs, which are costly to obtain. To minimize this cost, recent works thus often used…

Computation and Language · Computer Science 2020-09-22 Andreas Rücklé , Nafise Sadat Moosavi , Iryna Gurevych

In the quest for super-human performance, Large Language Models (LLMs) have traditionally been tethered to human-annotated datasets and predefined training objectives-a process that is both labor-intensive and inherently limited. This paper…

Computation and Language · Computer Science 2024-06-10 Ke Ji , Junying Chen , Anningzhe Gao , Wenya Xie , Xiang Wan , Benyou Wang

Large language models (LLMs) have garnered significant attention for their remarkable performance in a continuously expanding set of natural language processing tasks. However, these models have been shown to harbor inherent societal…

Computation and Language · Computer Science 2023-10-16 Abel Salinas , Louis Penafiel , Robert McCormack , Fred Morstatter

In safety-critical applications, language models should be able to characterize their uncertainty with meaningful probabilities. Many uncertainty quantification approaches require supervised data; however, finding suitable unseen…

Computation and Language · Computer Science 2026-05-14 Sophia Hager , Simon Zeng , Nicholas Andrews

Language models are pretrained as passive predictors with no incentive to model the consequences of their own outputs. Post-training changes this: a model producing its own responses can benefit from recognizing that it is on-policy. We…

Machine Learning · Computer Science 2026-05-26 Asvin G. , Jack Lindsey