English
Related papers

Related papers: Logit-Gap Steering: A Forward-Pass Diagnostic for …

200 papers

Large Language Models (LLMs) are prone to generating content that exhibits gender biases, raising significant ethical concerns. Alignment, the process of fine-tuning LLMs to better align with desired behaviors, is recognized as an effective…

Computation and Language · Computer Science 2024-12-17 Tao Zhang , Ziqian Zeng , Yuxiang Xiao , Huiping Zhuang , Cen Chen , James Foulds , Shimei Pan

Improving the reasoning capabilities of large language models (LLMs) typically requires supervised fine-tuning with labeled data or computationally expensive sampling. We introduce Unsupervised Prefix Fine-Tuning (UPFT), which leverages the…

Computation and Language · Computer Science 2025-03-05 Ke Ji , Jiahao Xu , Tian Liang , Qiuzhi Liu , Zhiwei He , Xingyu Chen , Xiaoyuan Liu , Zhijie Wang , Junying Chen , Benyou Wang , Zhaopeng Tu , Haitao Mi , Dong Yu

Maintaining predictive accuracy in non-stationary environments requires online model selection to adapt autonomously to unknown distribution shifts. However, existing tuning-free algorithms face a fundamental trade-off between robustness…

Machine Learning · Computer Science 2026-05-27 Kei Takemura , Ryuta Matsuno , Keita Sakuma

While there has been progress towards aligning Large Language Models (LLMs) with human values and ensuring safe behaviour at inference time, safety guards can easily be removed when fine tuned on unsafe and harmful datasets. While this…

We study grammar-constrained decoding (GCD) as a coupling between an autoregressive next-token distribution and a reachability oracle over a pushdown system compiled from a context-free grammar (CFG). We prove an oracle invariance theorem:…

Computation and Language · Computer Science 2026-03-09 Faruk Alpay , Bilge Senturk

Masked diffusion language models (MDLMs) generate text via iterative masked-token denoising, enabling mask-parallel decoding and distinct controllability and efficiency tradeoffs from autoregressive LLMs. Yet, efficient representation-level…

Computation and Language · Computer Science 2026-03-31 Adi Shnaidman , Erin Feiglin , Osher Yaari , Efrat Mentel , Amit Levi , Raz Lapid

Though deep neural networks have achieved the state of the art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. In this paper, we develop improved techniques…

Machine Learning · Computer Science 2021-09-09 Dou Goodman , Xingjian Li , Ji Liu , Dejing Dou , Tao Wei

Retrieval-augmented generation (RAG) grounds answers in retrieved passages, but retrieval is not verification: a passage can be topical and still fail to justify the answer. We frame this gap as evidence sufficiency verification for…

Computation and Language · Computer Science 2026-05-06 Jingxi Qiu , Zeyu Han , Cheng Huang

Recent advances in Large Language Models (LLMs) have led to impressive alignment where models learn to distinguish harmful from harmless queries through supervised finetuning (SFT) and reinforcement learning from human feedback (RLHF). In…

Artificial Intelligence · Computer Science 2025-06-18 Jiahao Yu , Haozheng Luo , Jerry Yao-Chieh Hu , Wenbo Guo , Han Liu , Xinyu Xing

Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations. While decomposed prompting is typically used to improve accuracy, we investigate its impact on…

Computation and Language · Computer Science 2026-02-05 Dhruv Madhwal , Lyuxin David Zhang , Dan Roth , Tomer Wolfson , Vivek Gupta

Large Language Models (LLMs) are deployed in high-stakes settings but can show demographic, gender, and geographic biases that undermine fairness and trust. Prior debiasing methods, including embedding-space projections, prompt-based…

Computation and Language · Computer Science 2026-03-24 Ravi Ranjan , Utkarsh Grover , Mayur Akewar , Xiaomin Lin , Agoritsa Polyzou

Direct preference optimization methods have emerged as a computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) for aligning Large Language Models (LLMs). Latest approaches have streamlined the alignment…

Machine Learning · Computer Science 2026-02-04 Maksim Afanasyev , Illarion Iov

Large reasoning models achieve strong performance on complex tasks by generating extended chains of thought, but they often "overthink": continuing to reason long after they have enough information to answer correctly. This wastes…

Computation and Language · Computer Science 2025-12-08 Ömer Faruk Akgül , Yusuf Hakan Kalaycı , Rajgopal Kannan , Willie Neiswanger , Viktor Prasanna

Code contains security and functional bugs. The process of identifying and localizing them is difficult and relies on human labor. In this work, we present a novel approach (FLAG) to assist human debuggers. FLAG is based on the lexical…

Cryptography and Security · Computer Science 2023-06-23 Baleegh Ahmad , Benjamin Tan , Ramesh Karri , Hammond Pearce

Tasks such as solving arithmetic equations, evaluating truth tables, and completing syllogisms are handled well by large language models (LLMs) in their standard form, but they often fail when the same problems are posed in logically…

Computation and Language · Computer Science 2026-02-03 Abhilekh Borah , Shubhra Ghosh , Kedar Joshi , Aditya Kumar Guru , Kripabandhu Ghosh

Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited. Typically, current open-source MLLMs rely on the alignment inherited from their language module to avoid harmful…

Cryptography and Security · Computer Science 2025-04-15 Yanbo Wang , Jiyang Guan , Jian Liang , Ran He

Readers of applied-domain LLM capability evaluations want to know what AI systems can currently do. That literature answers a related, but consequentially different, question: what older, cheaper, less-elicited models could do months or…

Computers and Society · Computer Science 2026-05-07 David Gringras , Misha Salahshoor

With the wide adoption of language models for IR -- and specifically RAG systems -- the latency of the underlying LLM becomes a crucial bottleneck, since the long contexts of retrieved passages lead large prompts and therefore, compute…

Information Retrieval · Computer Science 2026-04-06 Cornelius Kummer , Lena Jurkschat , Michael Färber , Sahar Vahdati

Instruction-tuned large language models produce helpful, structured responses, but how robust is this helpfulness under trivial constraints? We show that simple lexical constraints (banning a single punctuation character or common word)…

Computation and Language · Computer Science 2026-04-28 Erfan Baghaei Potraghloo , Seyedarmin Azizi , Souvik Kundu , Massoud Pedram

Despite their impressive capabilities, aligned large language models (LLMs) often generate outputs that lack diversity. What drives this consistency in the generation? We investigate this phenomenon through the lens of probability…

Computation and Language · Computer Science 2026-03-04 Chenghao Yang , Sida Li , Ari Holtzman
‹ Prev 1 8 9 10 Next ›