English
Related papers

Related papers: Comparative Analysis of LLM Abliteration Methods: …

200 papers

Large language models (LLMs) have achieved impressive capabilities, yet ensuring their safety against harmful prompts remains a critical challenge. Recent work has revealed that the latent representations (embeddings) of harmful and safe…

Computation and Language · Computer Science 2026-03-24 Xu Zhao , Xiting Wang , Weiran Shen

Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external corpora, which may lack quality, diversity, or demographic…

Computation and Language · Computer Science 2025-03-13 Liu Yu , Ludie Guo , Ping Kuang , Fan Zhou

With LLM usage becoming widespread across countries, languages, and humanity more broadly, the need to understand and guardrail their multilingual responses increases. Large-scale datasets for testing and benchmarking have been created to…

Computation and Language · Computer Science 2025-10-13 Kimaya Basu , Savi Kolari , Allison Yu

Modern software relies on a multitude of automated testing and quality assurance tools to prevent errors, bugs and potential vulnerabilities. This study sets out to provide a head-to-head, quantitative and qualitative evaluation of six…

Software Engineering · Computer Science 2025-08-07 Damian Gnieciak , Tomasz Szandala

The proliferation of Large Language Models (LLMs), such as ChatGPT, has raised concerns about their potential impact on academic integrity, prompting the need for LLM-resistant exam designs. This article investigates the performance of LLMs…

Computation and Language · Computer Science 2023-04-25 Simon kaare Larsen

Large Language Models (LLMs) can produce surprisingly sophisticated estimates of their own uncertainty. However, it remains unclear to what extent this expressed confidence is tied to the reasoning, knowledge, or decision making of the…

Machine Learning · Computer Science 2026-01-13 Jiawei Wang , Yanfei Zhou , Siddartha Devic , Deqing Fu

Few-shot learning is a challenging task that requires language models to generalize from limited examples. Large language models like GPT-3 and PaLM have made impressive progress in this area, but they still face difficulties in reasoning…

Computation and Language · Computer Science 2023-05-25 Yifei Li , Zeqi Lin , Shizhuo Zhang , Qiang Fu , Bei Chen , Jian-Guang Lou , Weizhu Chen

Despite efforts to expand the knowledge of large language models (LLMs), knowledge gaps -- missing or outdated information in LLMs -- might always persist given the evolving nature of knowledge. In this work, we study approaches to identify…

Computation and Language · Computer Science 2024-07-02 Shangbin Feng , Weijia Shi , Yike Wang , Wenxuan Ding , Vidhisha Balachandran , Yulia Tsvetkov

In this work, we introduce a novel evaluation paradigm for Large Language Models (LLMs) that compels them to transition from a traditional question-answering role, akin to a student, to a solution-scoring role, akin to a teacher. This…

Computation and Language · Computer Science 2024-06-06 Zhongshen Zeng , Pengguang Chen , Shu Liu , Haiyun Jiang , Jiaya Jia

The performance of large language models (LLMs) is closely linked to their underlying size, leading to ever-growing networks and hence slower inference. Speculative decoding has been proposed as a technique to accelerate autoregressive…

Large Language Models (LLMs) often produce outputs that -- though plausible -- can lack consistency and reliability, particularly in ambiguous or complex scenarios. Challenges arise from ensuring that outputs align with both factual…

Artificial Intelligence · Computer Science 2024-10-03 Weitong Zhang , Chengqi Zang , Bernhard Kainz

Large Language Models (LLMs) achieve strong performance on diverse tasks but often exhibit cognitive inertia, struggling to follow instructions that conflict with the standardized patterns learned during supervised fine-tuning (SFT). To…

In reasoning tasks, even a minor error can cascade into inaccurate results, leading to suboptimal performance of large language models in such domains. Earlier fine-tuning approaches sought to mitigate this by leveraging more precise…

Computation and Language · Computer Science 2024-07-12 Changyu Chen , Xiting Wang , Ting-En Lin , Ang Lv , Yuchuan Wu , Xin Gao , Ji-Rong Wen , Rui Yan , Yongbin Li

Recent large language models (LLMs) have been shown to be effective for misinformation detection. However, the choice of LLMs for experiments varies widely, leading to uncertain conclusions. In particular, GPT-4 is known to be strong in…

Computation and Language · Computer Science 2024-01-17 Tyler Vergho , Jean-Francois Godbout , Reihaneh Rabbany , Kellin Pelrine

This paper investigates the mathematical reasoning capabilities of large language models (LLMs) using 50 newly constructed high-school-level word problems. Unlike prior studies that focus solely on answer correctness, we rigorously analyze…

Artificial Intelligence · Computer Science 2025-02-24 Johan Boye , Birger Moell

Transliteration, the process of mapping text from one script to another, plays a crucial role in multilingual natural language processing, especially within linguistically diverse contexts such as India. Despite significant advancements…

Computation and Language · Computer Science 2025-05-27 Gulfarogh Azam , Mohd Sadique , Saif Ali , Mohammad Nadeem , Erik Cambria , Shahab Saquib Sohail , Mohammad Sultan Alam

Large Vision-Language Models (LVLMs) increasingly rely on retrieval to answer knowledge-intensive multimodal questions. Existing benchmarks overlook conflicts between visual and textual evidence and the importance of generating deflections…

Computation and Language · Computer Science 2026-04-15 Nicholas Moratelli , Christopher Davis , Leonardo F. R. Ribeiro , Bill Byrne , Gonzalo Iglesias

Large Language Models (LLMs) demonstrate promising capabilities in solving scientific problems but often suffer from the issue of hallucination. While integrating LLMs with tools can mitigate this issue, models fine-tuned on tool usage…

Machine Learning · Computer Science 2025-06-23 Bohan Lyu , Yadi Cao , Duncan Watson-Parris , Leon Bergen , Taylor Berg-Kirkpatrick , Rose Yu

The attack surface of a multimodal large language model (MLLM) is language-dependent in ways that reveal the mechanistic structure of alignment failures. We present the first systematic cross-lingual, multimodal red-teaming study comparing…

Computation and Language · Computer Science 2026-05-25 Casey Ford , Madison Van Doren , Sicheng Jin , Emily Dix

With the growing adoption of Large Language Models (LLMs) in critical areas, ensuring their security against jailbreaking attacks is paramount. While traditional defenses primarily rely on refusing malicious prompts, recent logit-level…

Cryptography and Security · Computer Science 2025-07-31 Yassine Rachidy , Jihad Rbaiti , Youssef Hmamouche , Faissal Sehbaoui , Amal El Fallah Seghrouchni
‹ Prev 1 4 5 6 7 8 10 Next ›