English
Related papers

Related papers: Decomposed Prompting Does Not Fix Knowledge Gaps, …

200 papers

Large language models are known to hallucinate when faced with unfamiliar queries, but the underlying mechanism that govern how models hallucinate are not yet fully understood. In this work, we find that unfamiliar examples in the models'…

Machine Learning · Computer Science 2024-05-30 Katie Kang , Eric Wallace , Claire Tomlin , Aviral Kumar , Sergey Levine

Verifying fact-checking claims poses a significant challenge, even for humans. Recent approaches have demonstrated that decomposing claims into relevant questions to gather evidence enhances the efficiency of the fact-checking process. In…

Computation and Language · Computer Science 2024-08-02 Ritvik Setty , Vinay Setty

Large language models (LLMs) trained on unfiltered corpora inherently risk retaining sensitive information, necessitating selective knowledge unlearning for regulatory compliance and ethical safety. However, existing parameter-modifying…

Machine Learning · Computer Science 2026-05-18 Zhaokun Wang , Jinyu Guo , Jingwen Pu , Hongli Pu , Meng Yang , Xunlei Chen , Jie Ou , Wenyi Li , Guangchun Luo , Wenhong Tian

Large language models (LLMs) are increasingly deployed in agentic and multi-turn workflows where they are tasked to perform actions of significant consequence. In order to deploy them reliably and manage risky outcomes in these settings, it…

Machine Learning · Computer Science 2026-02-10 Arka Pal , Teo Kitanovski , Arthur Liang , Akilesh Potti , Micah Goldblum

Most uncertainty-aware robotic systems collapse prediction uncertainty into a single scalar score and use it to trigger uniform corrective responses. This aggregation obscures whether uncertainty arises from corrupted observations or from…

Several recent papers have investigated the potential of language models as knowledge bases as well as the existence of severe biases when extracting factual knowledge. In this work, we focus on the factual probing performance over unseen…

Computation and Language · Computer Science 2024-04-02 Yijun Yang , Jie He , Pinzhen Chen , Víctor Gutiérrez-Basulto , Jeff Z. Pan

Code language models are increasingly adopted for both understanding and generative tasks. Despite their success, these models frequently produce overconfident incorrect predictions and underconfident correct predictions, undermining their…

Software Engineering · Computer Science 2026-05-20 Ravishka Rathnasuriya , Wei Yang

Recent studies suggest that self-reflective prompting can significantly enhance the reasoning capabilities of Large Language Models (LLMs). However, the use of external feedback as a stop criterion raises doubts about the true extent of…

Computation and Language · Computer Science 2024-04-16 Yanhong Li , Chenghao Yang , Allyson Ettinger

Motivated by the simultaneous association analysis with the presence of latent confounders, this paper studies the large-scale hypothesis testing problem for the high-dimensional confounded linear models with both non-asymptotic and…

Methodology · Statistics 2023-08-24 Yinrui Sun , Li Ma , Yin Xia

Unlearning has emerged as a critical capability for large language models (LLMs) to support data privacy, regulatory compliance, and ethical AI deployment. Recent techniques often rely on obfuscation by injecting incorrect or irrelevant…

Machine Learning · Computer Science 2025-09-10 Guangzhi Sun , Potsawee Manakul , Xiao Zhan , Mark Gales

Safety-aligned language models often refuse prompts that are actually harmless. Current evaluations mostly report global rates such as false rejection or compliance. These scores treat each prompt alone and miss local inconsistency, where a…

Computation and Language · Computer Science 2025-12-22 Riad Ahmed Anonto , Md Labid Al Nahiyan , Md Tanvir Hassan

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

Domain modeling, a crucial part of model-driven engineering, demands extensive domain knowledge and experience from engineers. When the system description is highly complicated, the modeling task can become particularly challenging and…

Software Engineering · Computer Science 2024-10-15 Ru Chen , Jingwei Shen , Xiao He

In the context of knowledge-driven seq-to-seq generation tasks, such as document-based question answering and document summarization systems, two fundamental knowledge sources play crucial roles: the inherent knowledge embedded within model…

Computation and Language · Computer Science 2025-01-16 Han Cao , Zhaoyang Zhang , Xiangtian Li , Chufan Wu , Hansong Zhang , Wenqing Zhang

Chain-of-thought prompting has demonstrated great success in facilitating the reasoning abilities of large language models. In this work, we explore how these enhanced reasoning abilities can be exploited to improve the robustness of large…

Computation and Language · Computer Science 2025-04-30 Wenxiao Wang , Parsa Hosseini , Soheil Feizi

We investigate the ability of language models to perform compositional reasoning tasks where the overall solution depends on correctly composing the answers to sub-problems. We measure how often models can correctly answer all sub-problems…

Computation and Language · Computer Science 2023-10-19 Ofir Press , Muru Zhang , Sewon Min , Ludwig Schmidt , Noah A. Smith , Mike Lewis

Large language models (LLMs) have advanced to encompass extensive knowledge across diverse domains. Yet controlling what a large language model should not know is important for ensuring alignment and thus safe use. However, accurately and…

Computation and Language · Computer Science 2024-11-01 Chris Yuhao Liu , Yaxuan Wang , Jeffrey Flanigan , Yang Liu

Large language models exhibit impressive reasoning capabilities yet frequently generate plausible but incorrect solutions, a phenomenon commonly termed hallucination. This paper investigates the effect of training objective composition on…

Machine Learning · Computer Science 2026-01-13 Murtaza Nikzad , Raghuram Ramanujan

As large language models (LLMs) gain popularity in conducting prediction tasks in-context, understanding the sources of uncertainty in in-context learning becomes essential to ensuring reliability. The recent hypothesis of in-context…

Machine Learning · Statistics 2025-12-08 I. Shavindra Jayasekera , Jacob Si , Filippo Valdettaro , Wenlong Chen , A. Aldo Faisal , Yingzhen Li

In this paper, we present our finding that prepending a Task-Agnostic Prefix Prompt (TAPP) to the input improves the instruction-following ability of various Large Language Models (LLMs) during inference. TAPP is different from canonical…

Computation and Language · Computer Science 2023-12-27 Seonghyeon Ye , Hyeonbin Hwang , Sohee Yang , Hyeongu Yun , Yireun Kim , Minjoon Seo