English
Related papers

Related papers: TRACE Back from the Future: A Probabilistic Reason…

200 papers

Recent advances in natural language processing highlight two key factors for improving reasoning in large language models (LLMs): (i) allocating more test-time compute tends to help on harder problems but often introduces redundancy in the…

Computation and Language · Computer Science 2025-11-04 Riccardo Alberghi , Elizaveta Demyanenko , Luca Biggio , Luca Saglietti

The general trace reconstruction problem seeks to recover an original sequence from its noisy copies independently corrupted by deletions, insertions, and substitutions. This problem arises in applications such as DNA data storage, a…

Machine Learning · Computer Science 2025-07-18 Franziska Weindel , Michael Girsch , Reinhard Heckel

Reliable mathematical and scientific reasoning remains an open challenge for large vision-language models. Standard final-answer evaluation often masks reasoning errors, allowing silent failures to persist. To address this gap, we introduce…

Artificial Intelligence · Computer Science 2025-12-15 Shima Imani , Seungwhan Moon , Lambert Mathias , Lu Zhang , Babak Damavandi

Trained on various human-authored corpora, Large Language Models (LLMs) have demonstrated a certain capability of reflecting specific human-like traits (e.g., personality or values) by prompting, benefiting applications like personalized…

Computation and Language · Computer Science 2025-12-01 Yuzhuo Bai , Shitong Duan , Muhua Huang , Jing Yao , Zhenghao Liu , Peng Zhang , Tun Lu , Xiaoyuan Yi , Maosong Sun , Xing Xie

Personalized generation with frozen large language models requires a conditioning signal that is both compact and current. Existing personalization methods typically retrieve or summarize user histories in text, or compress them into static…

Computation and Language · Computer Science 2026-05-27 Jinze Li , Xiaoyan Yang , Shuo Yang , Jinfeng Xu , Yue Shen , Jian Wang , Jinjie Gu , Edith Cheuk-Han Ngai

When language model (LM) users aim to improve the quality of its generations, it is crucial to specify concrete behavioral attributes that the model should strive to reflect. However, curating such principles across many domains, even…

Computation and Language · Computer Science 2025-11-17 Keshav Ramji , Tahira Naseem , Ramón Fernandez Astudillo

Multi-hop Knowledge Graph Question Answering (KGQA) requires coherent reasoning across relational paths, yet existing methods often treat each reasoning step independently and fail to effectively leverage experience from prior explorations,…

Computation and Language · Computer Science 2026-04-14 Yingxu Wang , Jiaxin Huang , Mengzhu Wang , Nan Yin

We present a Temporal Rule-Anchored Chain-of-Evidence (TRACE) on knowledge graphs for interpretable stock movement prediction that unifies symbolic relational priors, dynamic graph exploration, and LLM-guided decision making in a single…

Computational Engineering, Finance, and Science · Computer Science 2026-03-16 Qianggang Ding , Haochen Shi , Luis Castejón Lozano , Miguel Conner , Juan Abia , Luis Gallego-Ledesma , Joshua Fellowes , Gerard Conangla Planes , Adam Elwood , Bang Liu

Language models (LMs) are trained on billions of tokens in an attempt to recover the true language distribution. Still, vanilla random sampling from LMs yields low quality generations. Decoding algorithms attempt to restrict the LM…

Machine Learning · Computer Science 2026-01-06 Kareem Ahmed , Sameer Singh

Autoregressive models have demonstrated an unprecedented ability at modeling the intricacies of natural language. However, they continue to struggle with generating complex outputs that adhere to logical constraints. Sampling from a…

Machine Learning · Computer Science 2024-10-18 Kareem Ahmed , Kai-Wei Chang , Guy Van den Broeck

Assessing the reliability of Large Language Models (LLMs) by confidence elicitation is a prominent approach to AI safety in high-stakes applications, such as healthcare and finance. Existing methods either require expensive computational…

Computation and Language · Computer Science 2026-04-08 Zhaohan Zhang , Ziquan Liu , Ioannis Patras

Retrieval-augmented generation (RAG) has been extensively employed to mitigate hallucinations in large language models (LLMs). However, existing methods for multi-hop reasoning tasks often lack global planning, increasing the risk of…

Computation and Language · Computer Science 2025-11-14 Yijie Zhu , Haojie Zhou , Wanting Hong , Tailin Liu , Ning Wang

Evaluating open-ended outputs from large language models (LLMs) remains challenging due to the absence of ground truth. Existing metrics rely on final-answer accuracy or surface-level statistics, leaving the reasoning process itself…

Artificial Intelligence · Computer Science 2026-05-29 Yundong Kim , Heyoung Yang

Knowledge tracing aims to track students' knowledge status over time to predict students' future performance accurately. Markov chain-based knowledge tracking (MCKT) models can track knowledge concept mastery probability over time. However,…

Machine Learning · Computer Science 2023-02-20 Hengyu Liu , Tiancheng Zhang , Fan Li , Minghe Yu , Ge Yu

Large Language Models (LLMs) have been widely applied across multiple domains for their broad knowledge and strong reasoning capabilities. However, applying them to recommendation systems is challenging since it is hard for LLMs to extract…

Information Retrieval · Computer Science 2026-02-05 Yinan Zhang , Zhixi Chen , Jiazheng Jing , Zhiqi Shen

Autoregressive language models are next-token predictors and have been criticized for only optimizing surface plausibility (i.e., local coherence) rather than maintaining correct latent-state representations (i.e., global coherence).…

Computation and Language · Computer Science 2026-01-21 Xucong Hu , Jian-Qiao Zhu

Unstructured sparsity is now natively accelerated by recent GPU kernels and dataflow hardware, shifting the bottleneck from inference execution to the pruning algorithm. State-of-the-art methods for unstructured LLM pruning are layer-wise…

Machine Learning · Computer Science 2026-05-19 Mohammad Mozaffari , Younes Hourri , Mohammad Rastegari , Mahyar Najibi

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

Vision-Language Models (VLMs) struggle to translate high-level instructions into the precise spatial affordances required for robotic manipulation. While visual Chain-of-Thought (CoT) methods exist, they are often computationally intensive.…

Robotics · Computer Science 2025-11-05 Sangyun Park , Jin Kim , Yuchen Cui , Matthew S. Brown

Retrieval-augmented generation (RAG) has proven effective for knowledge-intensive tasks, but is widely believed to offer limited benefit for reasoning-intensive problems such as math and code generation. We challenge this assumption by…

Information Retrieval · Computer Science 2026-05-06 Negar Arabzadeh , Wenjie Ma , Sewon Min , Matei Zaharia