English
Related papers

Related papers: Navigating the OverKill in Large Language Models

200 papers

Despite exciting progress in causal language models, the expressiveness of the representations is largely limited due to poor discrimination ability. To remedy this issue, we present ContraCLM, a novel contrastive learning framework at both…

Large Language Models (LLMs) have shown remarkable capabilities in various natural language processing tasks. However, LLMs may rely on dataset biases as shortcuts for prediction, which can significantly impair their robustness and…

Computation and Language · Computer Science 2024-10-18 Yu Yuan , Lili Zhao , Kai Zhang , Guangting Zheng , Qi Liu

In this paper we motivate the causal mechanisms behind sample selection induced collider bias (selection collider bias) that can cause Large Language Models (LLMs) to learn unconditional dependence between entities that are unconditionally…

Computation and Language · Computer Science 2022-09-14 Emily McMilin

We propose a constraint learning schema for fine-tuning Large Language Models (LLMs) with attribute control. Given a training corpus and control criteria formulated as a sequence-level constraint on model outputs, our method fine-tunes the…

Computation and Language · Computer Science 2024-10-10 Tao Meng , Ninareh Mehrabi , Palash Goyal , Anil Ramakrishna , Aram Galstyan , Richard Zemel , Kai-Wei Chang , Rahul Gupta , Charith Peris

This study examines how Large Language Models (LLMs) perform when tackling quantitative management decision problems in a zero-shot setting. Drawing on 900 responses generated by five leading models across 20 diverse managerial scenarios,…

Computation and Language · Computer Science 2025-02-25 Jonathan Kuzmanko

In-context learning (ICL) has transformed the use of large language models (LLMs) for NLP tasks, enabling few-shot learning by conditioning on labeled examples without finetuning. Despite its effectiveness, ICL is prone to errors,…

Computation and Language · Computer Science 2025-03-21 Mario Sanz-Guerrero , Katharina von der Wense

Language models can be persuaded to abandon factual knowledge. This vulnerability is central to AI safety, but its internal mechanism remains poorly understood. We uncover a compact causal mechanism for persuasion-induced factual errors. A…

Artificial Intelligence · Computer Science 2026-05-12 Xiangkun Sun , Lingkai Kong , Aoqi Zhang , Liang Zeng , Tonghan Wang

Large language models exhibit surprising sensitivity to the structure of the prompt, but the mechanisms underlying this sensitivity remain poorly understood. In this work, we conduct an in-depth investigation on a striking case: in…

Computation and Language · Computer Science 2026-04-22 Hyunjong Ok , Jaeho Lee

Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks, from understanding to reasoning. However, they remain vulnerable to backdoor attacks, where…

Computation and Language · Computer Science 2024-11-28 Chen Chen , Yuchen Sun , Xueluan Gong , Jiaxin Gao , Kwok-Yan Lam

When we read, we make predictions about upcoming words; these predictions influence our reading behavior. The success of large language models (LLMs), which, like humans, make predictions about upcoming words, has motivated their use as…

Computation and Language · Computer Science 2026-05-27 Byung-Doh Oh , Tal Linzen

As Large Language Models (LLMs) play an increasingly pivotal role in natural language processing applications, their safety concerns become critical areas of NLP research. This paper presents Safety and Over-Defensiveness Evaluation (SODE)…

Computation and Language · Computer Science 2024-01-02 Neeraj Varshney , Pavel Dolin , Agastya Seth , Chitta Baral

Prompting inputs with natural language task descriptions has emerged as a popular mechanism to elicit reasonably accurate outputs from large-scale generative language models with little to no in-context supervision. This also helps gain…

Computation and Language · Computer Science 2023-08-17 Lisa Bauer , Karthik Gopalakrishnan , Spandana Gella , Yang Liu , Mohit Bansal , Dilek Hakkani-Tur

We introduce a method to reduce refusal rates of large language models (LLMs) on sensitive content without modifying model weights or prompts. Motivated by the observation that refusals in certain models were often preceded by the specific…

Computation and Language · Computer Science 2025-06-02 Harvey Dam , Jonas Knochelmann , Vinu Joseph , Ganesh Gopalakrishnan

The recent growth in the use of Large Language Models has made them vulnerable to sophisticated adversarial assaults, manipulative prompts, and encoded malicious inputs. Existing countermeasures frequently necessitate retraining models,…

Computation and Language · Computer Science 2026-03-10 Sheikh Samit Muhaimin , Spyridon Mastorakis

As the number of large language models (LLMs) released to the public grows, there is a pressing need to understand the safety implications associated with these models learning from third-party custom finetuning data. We explore the…

Computation and Language · Computer Science 2024-07-04 Jiachen Zhao , Zhun Deng , David Madras , James Zou , Mengye Ren

Large language models (LLMs) frequently produce false refusals, declining benign requests that contain terms resembling unsafe queries. We address this challenge by introducing two comprehensive benchmarks: the Exaggerated Safety Benchmark…

Computation and Language · Computer Science 2025-12-19 Shuzhou Yuan , Ercong Nie , Yinuo Sun , Chenxuan Zhao , William LaCroix , Michael Färber

Large language models (LLMs) can produce erroneous responses that sound fluent and convincing, raising the risk that users will rely on these responses as if they were correct. Mitigating such overreliance is a key challenge. Through a…

Human-Computer Interaction · Computer Science 2025-02-13 Sunnie S. Y. Kim , Jennifer Wortman Vaughan , Q. Vera Liao , Tania Lombrozo , Olga Russakovsky

Large Language Models (LLMs) have excelled at language understanding and generating human-level text. However, even with supervised training and human alignment, these LLMs are susceptible to adversarial attacks where malicious users can…

Computation and Language · Computer Science 2024-08-08 Shachi H Kumar , Saurav Sahay , Sahisnu Mazumder , Eda Okur , Ramesh Manuvinakurike , Nicole Beckage , Hsuan Su , Hung-yi Lee , Lama Nachman

Large Language Models (LLMs) trained with self-supervision on vast corpora of web text fit to the social biases of that text. Without intervention, these social biases persist in the model's predictions in downstream tasks, leading to…

Computation and Language · Computer Science 2023-12-13 Gustavo Gonçalves , Emma Strubell

Large language models (LLMs) have exploded in popularity in the past few years and have achieved undeniably impressive results on benchmarks as varied as question answering and text summarization. We provide a simple new prompting strategy…

Computation and Language · Computer Science 2022-12-14 Joshua Albrecht , Ellie Kitanidis , Abraham J. Fetterman