English
Related papers

Related papers: The Realignment Problem: When Right becomes Wrong …

200 papers

Retrieval-augmented large language models, when optimized with outcome-level rewards, can achieve strong answer accuracy on multi-hop questions. However, under noisy retrieval, models frequently suffer from "right-answer-wrong-reason…

Computation and Language · Computer Science 2026-03-17 Yu Liu , Wenxiao Zhang , Diandian Guo , Cong Cao , Fangfang Yuan , Qiang Sun , Yanbing Liu , Jin B. Hong , Zhiyuan Ma

Understanding when and how linguistic knowledge emerges during language model training remains a central challenge for interpretability. Most existing tools are post hoc, rely on scalar metrics, or require nontrivial integration effort,…

Computation and Language · Computer Science 2025-07-08 Nura Aljaafari , Danilo S. Carvalho , André Freitas

Modern transformer models exhibit phase transitions during training, distinct shifts from memorisation to abstraction, but the mechanisms underlying these transitions remain poorly understood. Prior work has often focused on endpoint…

Computation and Language · Computer Science 2025-05-26 Nura Aljaafari , Danilo S. Carvalho , André Freitas

Recent advancements in Large Language Models (LLMs) have expanded the horizons of natural language understanding and generation. Notably, the output control and alignment with the input of LLMs can be refined through instruction tuning.…

Computation and Language · Computer Science 2023-10-19 Ming Li , Lichang Chen , Jiuhai Chen , Shwai He , Heng Huang , Jiuxiang Gu , Tianyi Zhou

Large language models (LLMs) remain unreliable for global enterprise applications due to substantial performance gaps between high-resource and mid/low-resource languages, driven by English-centric pretraining and internal reasoning biases.…

Computation and Language · Computer Science 2025-10-28 Amit Agarwal , Hansa Meghwani , Hitesh Laxmichand Patel , Tao Sheng , Sujith Ravi , Dan Roth

The rapid progress in Large Language Models (LLMs) poses potential risks such as generating unethical content. Assessing LLMs' values can help expose their misalignment, but relies on reference-free evaluators, e.g., fine-tuned LLMs or…

Computation and Language · Computer Science 2024-07-16 Jing Yao , Xiaoyuan Yi , Xing Xie

Reinforcement learning from human feedback (RLHF) is a crucial technique in aligning large language models (LLMs) with human preferences, ensuring these LLMs behave in beneficial and comprehensible ways to users. However, a longstanding…

Artificial Intelligence · Computer Science 2024-03-27 Feiteng Fang , Liang Zhu , Min Yang , Xi Feng , Jinchang Hou , Qixuan Zhao , Chengming Li , Xiping Hu , Ruifeng Xu

Aligning large language models (LLMs) to human preferences is a crucial step in building helpful and safe AI tools, which usually involve training on supervised datasets. Popular algorithms such as Direct Preference Optimization (DPO) rely…

Computation and Language · Computer Science 2025-06-05 Honggen Zhang , Xufeng Zhao , Igor Molybog , June Zhang

Aligning large language models (LLMs) with human values is a vital task for LLM practitioners. Current alignment techniques have several limitations: (1) requiring a large amount of annotated data; (2) demanding heavy human involvement; (3)…

Computation and Language · Computer Science 2024-01-17 Hongyi Guo , Yuanshun Yao , Wei Shen , Jiaheng Wei , Xiaoying Zhang , Zhaoran Wang , Yang Liu

Large Language Models (LLMs) have showcased impressive performance. However, due to their inability to capture relationships among samples, these frozen LLMs inevitably keep repeating similar mistakes. In this work, we propose our…

Computation and Language · Computer Science 2023-10-25 Zeyuan Yang , Peng Li , Yang Liu

Personality manipulation in large language models (LLMs) is increasingly applied in customer service and agentic scenarios, yet its mechanisms and trade-offs remain unclear. We present a systematic study of personality control using the Big…

Computation and Language · Computer Science 2025-09-08 Gunmay Handa , Zekun Wu , Adriano Koshiyama , Philip Treleaven

Despite the fact that offline methods for Large Language Models (LLMs) alignment do not require a direct reward model, they remain susceptible to overoptimization. This issue arises when the trained model deviates excessively from the…

Recommender systems (RS) have become essential tools for helping users efficiently navigate the overwhelming amount of information on e-commerce and social platforms. However, traditional RS relying on Collaborative Filtering (CF) struggles…

Information Retrieval · Computer Science 2025-02-27 Mingdai Yang , Zhiwei Liu , Liangwei Yang , Xiaolong Liu , Chen Wang , Hao Peng , Philip S. Yu

Human preference alignment is essential to improve the interaction quality of large language models (LLMs). Existing alignment methods depend on manually annotated preference data to guide the LLM optimization directions. However,…

Computation and Language · Computer Science 2024-06-04 Pengyu Cheng , Yifan Yang , Jian Li , Yong Dai , Tianhao Hu , Peixin Cao , Nan Du , Xiaolong Li

Large Language Models (LLMs) have demonstrated promising capabilities as automatic evaluators in assessing the quality of generated natural language. However, LLMs still exhibit biases in evaluation and often struggle to generate coherent…

Computation and Language · Computer Science 2025-01-20 Yinhong Liu , Han Zhou , Zhijiang Guo , Ehsan Shareghi , Ivan Vulić , Anna Korhonen , Nigel Collier

Previous work adopts large language models (LLMs) as evaluators to evaluate natural language process (NLP) tasks. However, certain shortcomings, e.g., fairness, scope, and accuracy, persist for current LLM evaluators. To analyze whether…

Computation and Language · Computer Science 2025-01-22 Qintong Li , Leyang Cui , Lingpeng Kong , Wei Bi

Post-training (via supervised fine-tuning) improves instruction-following, but often induces semantic mode collapse by biasing models toward low-entropy fine-tuning data at the expense of the high-entropy pretraining distribution.…

Large Language Models (LLMs) have shown superior performance in various applications and fields. To achieve better performance on specialized domains such as law and advertisement, LLMs are often continue pre-trained on in-domain data.…

Computation and Language · Computer Science 2024-06-25 Xiao Liang , Xinyu Hu , Simiao Zuo , Yeyun Gong , Qiang Lou , Yi Liu , Shao-Lun Huang , Jian Jiao

Large language models (LLMs) have become integral to modern software development, enabling automated code generation at scale. However, validating the correctness of LLM-generated code remains a critical and largely unsolved challenge.…

Software Engineering · Computer Science 2026-05-29 Tambon Florian , Papadakis Mike

Recent advancements in large language models (LLMs) have significantly enhanced the ability of LLM-based systems to perform complex tasks through natural language processing and tool interaction. However, optimizing these LLM-based systems…

Computation and Language · Computer Science 2025-06-19 Peiyan Zhang , Haibo Jin , Leyang Hu , Xinnuo Li , Liying Kang , Man Luo , Yangqiu Song , Haohan Wang