English
Related papers

Related papers: Testing the Limits of Truth Directions in LLMs

200 papers

The performance of Large language models (LLMs) across a broad range of domains has been impressive but have been critiqued as not being able to reason about their process and conclusions derived. This is to explain the conclusions draw,…

Computation and Language · Computer Science 2024-10-30 Rob Sullivan , Nelly Elsayed

Language model representations often contain linear directions that correspond to high-level concepts. Here, we study the dynamics of these representations: how representations evolve along these dimensions within the context of (simulated)…

Computation and Language · Computer Science 2026-02-04 Andrew Kyle Lampinen , Yuxuan Li , Eghbal Hosseini , Sangnie Bhardwaj , Murray Shanahan

We are interested in understanding how well Transformer language models (TLMs) can perform reasoning tasks when trained on knowledge encoded in the form of natural language. We investigate their systematic generalization abilities on a…

Machine Learning · Computer Science 2020-10-22 Nicolas Gontier , Koustuv Sinha , Siva Reddy , Christopher Pal

For Large Language Models (LLMs) to be reliable, they must learn robust knowledge that can be generally applied in diverse settings -- often unlike those seen during training. Yet, extensive research has shown that LLM performance can be…

Computation and Language · Computer Science 2025-10-15 Patrick Haller , Mark Ibrahim , Polina Kirichenko , Levent Sagun , Samuel J. Bell

Large Language Models (LLMs) have revolutionized artificial intelligence, demonstrating remarkable computational power and linguistic capabilities. However, these models are inherently prone to various biases stemming from their training…

Computation and Language · Computer Science 2025-02-14 Riccardo Cantini , Giada Cosenza , Alessio Orsino , Domenico Talia

Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. However, their internal mechanisms are still unclear and this lack of transparency poses unwanted risks for downstream applications.…

Computation and Language · Computer Science 2023-11-30 Haiyan Zhao , Hanjie Chen , Fan Yang , Ninghao Liu , Huiqi Deng , Hengyi Cai , Shuaiqiang Wang , Dawei Yin , Mengnan Du

Due to the black-box nature of large language models (LLMs) and the realism of their generated content, issues such as hallucinations, bias, unfairness, and copyright infringement have become significant. In this context, sourcing…

Computation and Language · Computer Science 2026-01-01 Liang Pang , Jia Gu , Sunhao Dai , Zihao Wei , Zenghao Duan , Kangxi Wu , Zhiyi Yin , Jun Xu , Huawei Shen , Xueqi Cheng

Large Language Models (LLMs) are important tools for reasoning and problem-solving, while they often operate passively, answering questions without actively discovering new ones. This limitation reduces their ability to simulate human-like…

Computational Engineering, Finance, and Science · Computer Science 2025-09-26 Hong Su

Detecting hallucinations in large language models (LLMs) remains a fundamental challenge for their trustworthy deployment. Going beyond basic uncertainty-driven hallucination detection frameworks, we propose a simple yet powerful method…

Artificial Intelligence · Computer Science 2025-10-10 Rui Wang , Zeming Wei , Guanzhang Yue , Meng Sun

Large Language Models (LLMs) show impressive inductive reasoning capabilities, enabling them to generate hypotheses that could generalize effectively to new instances when guided by in-context demonstrations. However, in real-world…

Artificial Intelligence · Computer Science 2024-12-19 Zhuo Liu , Ding Yu , Hangfeng He

Large Language Models (LLMs) are extensively used today across various sectors, including academia, research, business, and finance, for tasks such as text generation, summarization, and translation. Despite their widespread adoption, these…

Computation and Language · Computer Science 2024-04-26 Yash Saxena , Sarthak Chopra , Arunendra Mani Tripathi

This paper investigates the reliability of explanations generated by large language models (LLMs) when prompted to explain their previous output. We evaluate two kinds of such self-explanations - extractive and counterfactual - using three…

Computation and Language · Computer Science 2025-02-03 Korbinian Randl , John Pavlopoulos , Aron Henriksson , Tony Lindgren

Advancements in Large Language Models (LLMs) have increased the performance of different natural language understanding as well as generation tasks. Although LLMs have breached the state-of-the-art performance in various tasks, they often…

Computation and Language · Computer Science 2025-05-28 Charaka Vinayak Kumar , Ashok Urlana , Gopichand Kanumolu , Bala Mallikarjunarao Garlapati , Pruthwik Mishra

Despite the widespread adoption of large language models (LLMs) for recommendation, we demonstrate that LLMs often exhibit uncertainty in their recommendations. To ensure the trustworthy use of LLMs in generating recommendations, we…

Information Retrieval · Computer Science 2025-02-13 Wonbin Kweon , Sanghwan Jang , SeongKu Kang , Hwanjo Yu

The capabilities and limitations of Large Language Models have been sketched out in great detail in recent years, providing an intriguing yet conflicting picture. On the one hand, LLMs demonstrate a general ability to solve problems. On the…

While Large language models (LLMs) have proved able to address some complex reasoning tasks, we also know that they are highly sensitive to input variation, which can lead to different solution paths and final answers. Answer consistency…

Computation and Language · Computer Science 2025-03-05 Huiyuan Lai , Xiao Zhang , Malvina Nissim

Large language models (LLMs) frequently generate confident yet inaccurate responses, introducing significant risks for deployment in safety-critical domains. We present a novel, test-time approach to detecting model hallucination through…

Machine Learning · Computer Science 2025-10-07 Hazel Kim , Tom A. Lamb , Adel Bibi , Philip Torr , Yarin Gal

Large Language Models (LLMs) are increasingly employed for simulating human behaviors across diverse domains. However, our position is that current LLM-based human simulations remain insufficiently reliable, as evidenced by significant…

Computation and Language · Computer Science 2025-12-02 Qian Wang , Jiaying Wu , Zichen Jiang , Zhenheng Tang , Bingqiao Luo , Nuo Chen , Wei Chen , Bingsheng He

Recent work utilizes Large Language Models (LLMs) for topic modeling, generating comprehensible topic labels for given documents. However, their performance has mainly been evaluated qualitatively, and there remains room for quantitative…

Computation and Language · Computer Science 2024-06-26 Tomoki Doi , Masaru Isonuma , Hitomi Yanaka

Large Language Models (LLMs) have achieved remarkable success, where instruction tuning is the critical step in aligning LLMs with user intentions. In this work, we investigate how the instruction tuning adjusts pre-trained models with a…

Computation and Language · Computer Science 2024-04-05 Xuansheng Wu , Wenlin Yao , Jianshu Chen , Xiaoman Pan , Xiaoyang Wang , Ninghao Liu , Dong Yu
‹ Prev 1 8 9 10 Next ›