English
Related papers

Related papers: Untying the Reversal Curse via Bidirectional Langu…

200 papers

The reversal curse describes a failure of autoregressive language models to retrieve a fact in reverse order (e.g., training on ``$A > B$'' but failing on ``$B < A$''). Recent work shows that objectives with bidirectional supervision (e.g.,…

Computation and Language · Computer Science 2026-04-08 Julian Coda-Forno , Jane X. Wang , Arslan Chaudhry

While large language models (LLMs) showcase unprecedented capabilities, they also exhibit certain inherent limitations when facing seemingly trivial tasks. A prime example is the recently debated "reversal curse", which surfaces when…

Computation and Language · Computer Science 2024-11-25 Zhengkai Lin , Zhihang Fu , Kai Liu , Liang Xie , Binbin Lin , Wenxiao Wang , Deng Cai , Yue Wu , Jieping Ye

The reversal curse--a language model's inability to infer an unseen fact "B is A" from a learned fact "A is B"--is widely considered a fundamental limitation. We show that this is not an inherent failure but an artifact of how models encode…

Artificial Intelligence · Computer Science 2026-03-03 Dong-Kyum Kim , Minsung Kim , Jea Kwon , Nakyeong Yang , Meeyoung Cha

Knowledge editing methods (KEs) are a cost-effective way to update the factual content of large language models (LLMs), but they pose a dual-use risk. While KEs are beneficial for updating outdated or incorrect information, they can be…

Computation and Language · Computer Science 2026-03-02 Paul Youssef , Zhixue Zhao , Christin Seifert , Jörg Schlötterer

The term "Reversal Curse" refers to the scenario where auto-regressive decoder large language models (LLMs), such as ChatGPT, trained on "A is B" fail to learn "B is A," assuming that B and A are distinct and can be uniquely identified from…

Computation and Language · Computer Science 2024-07-03 Da Wu , Jingye Yang , Kai Wang

Auto-regressive large language models (LLMs) show impressive capacities to solve many complex reasoning tasks while struggling with some simple logical reasoning tasks such as inverse search: when trained on '$A \to B$' (e.g., 'Tom is the…

Machine Learning · Computer Science 2024-10-29 Hanlin Zhu , Baihe Huang , Shaolun Zhang , Michael Jordan , Jiantao Jiao , Yuandong Tian , Stuart Russell

Autoregressive large language models (LLMs) have achieved remarkable success in many complex tasks, yet they can still fail in very simple logical reasoning such as the "reversal curse" -- when trained on forward knowledge data of the form…

Artificial Intelligence · Computer Science 2026-02-03 Xutao Ma , Yixiao Huang , Hanlin Zhu , Somayeh Sojoudi

The "reversal curse" refers to the phenomenon where large language models (LLMs) exhibit predominantly unidirectional behavior when processing logically bidirectional relationships. Prior work attributed this to autoregressive training --…

Computation and Language · Computer Science 2026-01-13 Shaokai He , Kaiwen Wei , Xinyi Zeng , Xiang Chen , Xue Yang , Zhenyang Li , Jiang Zhong , Yu Tian

Large language models (LLMs) have a surprising failure: when trained on "A has a feature B", they do not generalize to "B is a feature of A", which is termed the Reversal Curse. Even when training with trillions of tokens this issue still…

Computation and Language · Computer Science 2024-05-09 Olga Golovneva , Zeyuan Allen-Zhu , Jason Weston , Sainbayar Sukhbaatar

Recent research observed a noteworthy phenomenon in large language models (LLMs), referred to as the ``reversal curse.'' The reversal curse is that when dealing with two entities, denoted as $a$ and $b$, connected by their relation $R$ and…

Computation and Language · Computer Science 2024-11-12 Ang Lv , Kaiyi Zhang , Shufang Xie , Quan Tu , Yuhan Chen , Ji-Rong Wen , Rui Yan

While large language models (LLMs) have achieved impressive performance across diverse tasks, recent studies showcase that causal LLMs suffer from the "reversal curse". It is a typical example that the model knows "A's father is B", but is…

Computation and Language · Computer Science 2024-03-21 Qingyan Guo , Rui Wang , Junliang Guo , Xu Tan , Jiang Bian , Yujiu Yang

Knowledge editing aims to change language models' performance on several special cases (i.e., editing scope) by infusing the corresponding expected knowledge into them. With the recent advancements in large language models (LLMs), knowledge…

Computation and Language · Computer Science 2024-05-31 Jiaan Wang , Yunlong Liang , Zengkui Sun , Yuxuan Cao , Jiarong Xu , Fandong Meng

Humans are accustomed to reading and writing in a forward manner, and this natural bias extends to text understanding in auto-regressive large language models (LLMs). This paper investigates whether LLMs, like humans, struggle with reverse…

Computation and Language · Computer Science 2025-02-25 Sicheng Yu , Yuanchen Xu , Cunxiao Du , Yanying Zhou , Minghui Qiu , Qianru Sun , Hao Zhang , Jiawei Wu

Despite their impressive capabilities, LLMs exhibit a basic generalization failure known as the Reversal Curse, where they struggle to learn reversible factual associations. Understanding why this occurs could help identify weaknesses in…

Computation and Language · Computer Science 2026-02-11 Boshi Wang , Huan Sun

Autoregressive language models (ARMs) suffer from the reversal curse: after learning ''$A$ is $B$,'' they often fail on the reverse query ''$B$ is $A$.'' Masked diffusion language models (MDMs) exhibit this failure in a much weaker form,…

Artificial Intelligence · Computer Science 2026-05-13 Moongyu Jeon , Sangwoo Shin , BumJun Kim , Kyelim Lee , Albert No

Model editing is a technique that edits the large language models (LLMs) with updated knowledge to alleviate hallucinations without resource-intensive retraining. While current model editing methods can effectively modify a model's behavior…

Computation and Language · Computer Science 2024-10-08 Jia-Chen Gu , Hao-Xiang Xu , Jun-Yu Ma , Pan Lu , Zhen-Hua Ling , Kai-Wei Chang , Nanyun Peng

We introduce the concept of the self-referencing causal cycle (abbreviated RECALL) - a mechanism that enables large language models (LLMs) to bypass the limitations of unidirectional causality, which underlies a phenomenon known as the…

Knowledge editing aims to update the embedded knowledge within Large Language Models (LLMs). However, existing approaches, whether through parameter modification or external memory integration, often suffer from inconsistent evaluation…

Computation and Language · Computer Science 2025-05-27 Guoxiu He , Xin Song , Futing Wang , Aixin Sun

Today's best language models still struggle with hallucinations: factually incorrect generations, which impede their ability to reliably retrieve information seen during training. The reversal curse, where models cannot recall information…

Machine Learning · Computer Science 2024-06-11 Ouail Kitouni , Niklas Nolte , Diane Bouchacourt , Adina Williams , Mike Rabbat , Mark Ibrahim

In-context knowledge editing (IKE) enables efficient modification of large language model (LLM) outputs without parameter changes and at zero-cost. However, it can be misused to manipulate responses opaquely, e.g., insert misinformation or…

Computation and Language · Computer Science 2025-04-11 Paul Youssef , Zhixue Zhao , Jörg Schlötterer , Christin Seifert
‹ Prev 1 2 3 10 Next ›