English
Related papers

Related papers: Lookahead Path Likelihood Optimization for Diffusi…

200 papers

We present an outcome-driven fine-tuning framework that enhances the forecasting capabilities of large language models (LLMs) without relying on human-curated reasoning samples. Our method leverages model self-play to generate pairs of…

Computation and Language · Computer Science 2025-02-11 Benjamin Turtel , Danny Franklin , Philipp Schoenegger

Diffusion Language Models (DLMs) generate text by iteratively denoising a masked sequence, repeatedly deciding which positions to commit at each step. Standard decoding follows a greedy rule: unmask the most confident positions, yet this…

Computation and Language · Computer Science 2026-02-26 Mingyu Cao , Alvaro H. C. Correia , Christos Louizos , Shiwei Liu , Lu Yin

Discrete diffusion language models (dLLMs) accelerate text generation by unmasking multiple tokens in parallel. However, parallel decoding introduces a distributional mismatch: it approximates the joint conditional using a fully factorized…

Computation and Language · Computer Science 2026-04-06 Liran Ringel , Ameen Ali , Yaniv Romano

Multiple choice questions (MCQs) are a popular and important task for evaluating large language models (LLMs). Based on common strategies people use when answering MCQs, the process of elimination (PoE) has been proposed as an effective…

Computation and Language · Computer Science 2025-05-20 Zhenhao Zhu , Bulou Liu , Qingyao Ai , Yiqun Liu

Large language models (LLMs) have shown strong performance in many reasoning benchmarks. However, recent studies have pointed to memorization, rather than generalization, as one of the leading causes for such performance. LLMs, in fact, are…

Computation and Language · Computer Science 2025-09-19 Xingwei Tan , Marco Valentino , Mahmud Akhter , Maria Liakata , Nikolaos Aletras

Diffusion language models (DLMs) have recently emerged as a compelling alternative to autoregressive generation, offering parallel generation and improved global coherence. During inference, DLMs generate text by iteratively denoising…

Diffusion Large Language Models (dLLMs) have demonstrated significant potential for high-speed inference. However, current confidence-driven decoding strategies are constrained by limited parallelism, typically achieving only 1--3 tokens…

Computation and Language · Computer Science 2025-12-23 Chenkai Xu , Yijie Jin , Jiajun Li , Yi Tu , Guoping Long , Dandan Tu , Mingcong Song , Hongjie Si , Tianqi Hou , Junchi Yan , Zhijie Deng

While diffusion language models (DLMs) have achieved competitive performance in text generation, improving their reasoning ability with reinforcement learning remains an active research area. Here, we introduce d2, a reasoning framework…

Machine Learning · Computer Science 2026-02-10 Guanghan Wang , Gilad Turok , Yair Schiff , Marianne Arriola , Volodymyr Kuleshov

Offline preference optimization is a key method for enhancing and controlling the quality of Large Language Model (LLM) outputs. Typically, preference optimization is approached as an offline supervised learning task using manually-crafted…

Machine Learning · Computer Science 2024-11-05 Chris Lu , Samuel Holt , Claudio Fanconi , Alex J. Chan , Jakob Foerster , Mihaela van der Schaar , Robert Tjarko Lange

Large language models achieve strong reasoning performance, but inference strategies such as Self-Consistency (SC) are computationally expensive, as they fully expand all reasoning traces. We introduce PoLR (Path of Least Resistance), the…

Artificial Intelligence · Computer Science 2026-02-04 Ishan Jindal , Sai Prashanth Akuthota , Jayant Taneja , Sachin Dev Sharma

Large Language Models (LLMs) are increasingly being used in real-world applications. However, concerns about the reliability of the content they generate persist, as it frequently deviates from factual correctness or exhibits deficiencies…

Computation and Language · Computer Science 2025-03-05 Yunzhen He , Yusuke Takase , Yoichi Ishibashi , Hidetoshi Shimodaira

While likelihood is attractive in theory, its estimates by deep generative models (DGMs) are often broken in practice, and perform poorly for out of distribution (OOD) Detection. Various recent works started to consider alternative scores…

Machine Learning · Computer Science 2024-01-11 Sicong Huang , Jiawei He , Kry Yik Chau Lui

We propose DiFFPO, Diffusion Fast and Furious Policy Optimization, a unified framework for training masked diffusion large language models (dLLMs) to reason not only better (furious), but also faster via reinforcement learning (RL). We…

Machine Learning · Computer Science 2026-01-13 Hanyang Zhao , Dawen Liang , Wenpin Tang , David Yao , Nathan Kallus

Large language models (LLMs) have shown remarkable in-context learning (ICL) capabilities, yet their potential for sequential decision-making remains underexplored. In this paper, we study the ICL capabilities of LLMs in sequential…

Machine Learning · Computer Science 2026-05-12 Minmin Zhang , Sina Aghaei , Soroush Saghafian

Diffusion Language Models (DLMs) offer order-agnostic generation that can explore many possible decoding trajectories. However, current decoding methods commit to a single trajectory, limiting exploration in trajectory space. We introduce…

Computation and Language · Computer Science 2026-02-06 Yangyi Shen , Tianjian Feng , Jiaqi Han , Wen Wang , Tianlang Chen , Chunhua Shen , Jure Leskovec , Stefano Ermon

Direct Preference Optimisation (DPO) is effective at significantly improving the performance of large language models (LLMs) on downstream tasks such as reasoning, summarisation, and alignment. Using pairs of preferred and dispreferred…

Computation and Language · Computer Science 2024-07-04 Arka Pal , Deep Karkhanis , Samuel Dooley , Manley Roberts , Siddartha Naidu , Colin White

The Large language models (LLMs) have showcased superior capabilities in sophisticated tasks across various domains, stemming from basic question-answer (QA), they are nowadays used as decision assistants or explainers for unfamiliar…

Computation and Language · Computer Science 2024-07-09 Longchao Da , Tiejin Chen , Lu Cheng , Hua Wei

Standard autoregressive decoding in large language models (LLMs) is inherently short-sighted, often failing to find globally optimal reasoning paths due to its token-by-token generation process. While inference-time strategies like…

Machine Learning · Computer Science 2026-01-23 Huayu Li , ZhengXiao He , Siyuan Tian , Jinghao Wen , Ao Li

Large language models (LLMs) possess vast semantic knowledge but often struggle with complex reasoning tasks, particularly in relational reasoning problems such as kinship or spatial reasoning. In this paper, we present Path-of-Thoughts…

Computation and Language · Computer Science 2026-03-25 Ge Zhang , Mohammad Ali Alomrani , Hongjian Gu , Jiaming Zhou , Yaochen Hu , Bin Wang , Qun Liu , Mark Coates , Yingxue Zhang , Jianye Hao

Recently, sequential recommendation has been adapted to the LLM paradigm to enjoy the power of LLMs. LLM-based methods usually formulate recommendation information into natural language and the model is trained to predict the next item in…

Information Retrieval · Computer Science 2024-02-16 Hanbing Wang , Xiaorui Liu , Wenqi Fan , Xiangyu Zhao , Venkataramana Kini , Devendra Yadav , Fei Wang , Zhen Wen , Jiliang Tang , Hui Liu