English
Related papers

Related papers: TRACER: Verifiable Generative Provenance for Multi…

200 papers

Reward models are critical for aligning vision-language systems with human preferences, yet current approaches suffer from hallucination, weak visual grounding, and an inability to use tools for verification, limiting their reliability on…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Shengyuan Ding , Xinyu Fang , Ziyu Liu , Yuhang Zang , Yuhang Cao , Xiangyu Zhao , Haodong Duan , Xiaoyi Dong , Jianze Liang , Bin Wang , Conghui He , Dahua Lin , Jiaqi Wang

Recent deep research systems have improved the ability of large language models to produce long, grounded reports through iterative retrieval and reasoning. However, most text-centered systems rely mainly on textual evidence, while…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Zhuofan Shi , Peilun Jia , Baoqin Sun , Haiyang Shen , Sixiong Xie , Yun Ma , Xiang Jing

When a multi-agent system produces an incorrect or harmful answer, who is accountable if execution logs and agent identifiers are unavailable? In practice, generated content is often detached from its execution environment due to privacy or…

Artificial Intelligence · Computer Science 2026-04-02 Yi Nian , Haosen Cao , Shenzhe Zhu , Henry Peng Zou , Qingqing Luan , Yue Zhao

Retrieval-Augmented Generation (RAG) grounds Large Language Models (LLMs) in external knowledge but often suffers from flat context representations and stateless retrieval, leading to unstable performance. We propose Stateful…

Computation and Language · Computer Science 2026-04-17 Qi Dong , Ziheng Lin , Ning Ding

Unified multimodal models integrate the reasoning capacity of large language models with both image understanding and generation, showing great promise for advanced multimodal intelligence. However, the community still lacks a rigorous…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Hongxiang Li , Yaowei Li , Bin Lin , Yuwei Niu , Yuhang Yang , Xiaoshuang Huang , Jiayin Cai , Xiaolong Jiang , Yao Hu , Long Chen

Large language models handle single-turn generation well, but multi-turn interactions still require the model to reconstruct user intent and task state from an expanding token history because internal representations do not persist across…

Computation and Language · Computer Science 2025-12-11 Vishwas Hegde , Vindhya Shigehalli

Reasoning in language models is difficult to evaluate: natural-language traces are unverifiable, symbolic datasets are too small, and most benchmarks conflate heuristics with inference. We present FOL-Traces, the first large-scale dataset…

Artificial Intelligence · Computer Science 2026-01-27 Isabelle Lee , Sarah Liaw , Dani Yogatama

When applied to open-domain question answering, large language models (LLMs) frequently generate incorrect responses based on made-up facts, which are called $\textit{hallucinations}$. Retrieval augmented generation (RAG) is a promising…

Computation and Language · Computer Science 2024-04-09 Shuo Li , Sangdon Park , Insup Lee , Osbert Bastani

Chain-of-Thought reasoning significantly improves the performance of large language models on complex tasks, but incurs high inference latency due to long generation traces. Step-level speculative reasoning aims to mitigate this cost, yet…

Computation and Language · Computer Science 2026-02-24 Siran Liu , Cyril Y. He

Multi-hop question answering is a challenging task in which language models must reason over multiple steps to reach the correct answer. With the help of Large Language Models and their reasoning capabilities, existing systems are able to…

Machine Learning · Computer Science 2025-12-08 Durga Prasad Maram , Kalpa Gunaratna , Vijay Srinivasan , Haris Jeelani , Srinivas Chappidi

Tool-using LLM agents produce trajectories whose calls form a directed dependency graph: earlier tool outputs supply arguments to later calls. Whether this execution structure is represented inside the model is unknown; prior structural…

Computation and Language · Computer Science 2026-05-26 Tianda Sun , Dimitar Kazakov

Many text generation systems benefit from using a retriever to retrieve passages from a textual knowledge corpus (e.g., Wikipedia) which are then provided as additional context to the generator. For open-ended generation tasks (like…

Computation and Language · Computer Science 2021-10-22 Ashwin Paranjape , Omar Khattab , Christopher Potts , Matei Zaharia , Christopher D. Manning

Agent traces carry increasing analytical value in agentic systems and context engineering, yet most prior work treats conversation format as a trivial implementation detail. Modern agent conversations, however, contain deeply structured…

Artificial Intelligence · Computer Science 2026-04-02 Lvmin Zhang , Maneesh Agrawala

This paper argues that generating output tokens is more effective than using pooled representations for prediction tasks because token-level generation retains more mutual information. Since LLMs are trained on massive text corpora using…

Sequence generation applications require satisfying semantic constraints, such as ensuring that programs are correct, using certain keywords, or avoiding undesirable content. Language models, whether fine-tuned or prompted with few-shot…

Computation and Language · Computer Science 2022-11-02 Sean Welleck , Ximing Lu , Peter West , Faeze Brahman , Tianxiao Shen , Daniel Khashabi , Yejin Choi

Despite rapid progress in claim verification, we lack a systematic understanding of what reasoning these benchmarks actually exercise. We generate structured reasoning traces for 24K claim-verification examples across 9 datasets using…

Computation and Language · Computer Science 2026-04-03 Delip Rao , Chris Callison-Burch

Content is created for a well-defined purpose, often described by a metric or signal represented in the form of structured information. The relationship between the goal (metrics) of target content and the content itself is non-trivial.…

Computation and Language · Computer Science 2022-03-29 Navita Goyal , Roodram Paneri , Ayush Agarwal , Udit Kalani , Abhilasha Sancheti , Niyati Chhaya

Large language models have achieved high performance on various question answering (QA) benchmarks, but the explainability of their output remains elusive. Structured explanations, called entailment trees, were recently suggested as a way…

Computation and Language · Computer Science 2022-07-21 Danilo Ribeiro , Shen Wang , Xiaofei Ma , Rui Dong , Xiaokai Wei , Henry Zhu , Xinchi Chen , Zhiheng Huang , Peng Xu , Andrew Arnold , Dan Roth

Large Language Models (LLMs) deployed in agentic environments must exercise multiple capabilities across different task instances, where a capability is performing one or more actions in a trajectory that are necessary for successfully…

Artificial Intelligence · Computer Science 2026-04-08 Hangoo Kang , Tarun Suresh , Jon Saad-Falcon , Azalia Mirhoseini

Recently developed pretrained models can encode rich world knowledge expressed in multiple modalities, such as text and images. However, the outputs of these models cannot be integrated into algorithms to solve sequential decision-making…

Artificial Intelligence · Computer Science 2024-06-19 Yunhao Yang , Cyrus Neary , Ufuk Topcu