English
Related papers

Related papers: The Detection-Extraction Gap: Models Know the Answ…

200 papers

Prompting methods for language models, such as Chain-of-thought (CoT), present intuitive step-by-step processes for problem solving. These methodologies aim to equip models with a better understanding of the correct procedures for…

Computation and Language · Computer Science 2025-08-26 Jason Li , Lauren Yraola , Kevin Zhu , Sean O'Brien

As large language models are deployed as autonomous agents with tool execution privileges, a critical assumption underpins their security architecture: that model errors are detectable at runtime. We present empirical evidence that this…

Artificial Intelligence · Computer Science 2026-03-24 Gregory M. Ruddell

Increasing the thinking budget of AI models can significantly improve accuracy, but not all questions warrant the same amount of reasoning. Users may prefer to allocate different amounts of reasoning effort depending on how they value…

Artificial Intelligence · Computer Science 2025-11-13 Michael Kleinman , Matthew Trager , Alessandro Achille , Wei Xia , Stefano Soatto

Mixture-of-Experts (MoE) architectures decouple model capacity from per-token computation, enabling scaling beyond the computational limits imposed by dense scaling laws. Yet how MoE architectures shape knowledge acquisition during…

Artificial Intelligence · Computer Science 2026-01-14 Bo Wang , Junzhuo Li , Hong Chen , Yuanlin Chu , Yuxuan Fan , Xuming Hu

We discover a theoretical connection between explanation estimation and distribution compression that significantly improves the approximation of feature attributions, importance, and effects. While the exact computation of various machine…

Machine Learning · Computer Science 2025-01-24 Hubert Baniecki , Giuseppe Casalicchio , Bernd Bischl , Przemyslaw Biecek

Large Reasoning Models (LRMs) achieve strong performance by generating long chains of thought (CoT), but often overthink, continuing to reason after a solution has already stabilized and thereby wasting tokens and increasing latency.…

Computation and Language · Computer Science 2026-05-19 Dehai Min , Giovanni Vaccarino , Huiyi Chen , Yongliang Wu , Gal Yona , Lu Cheng

As language models accelerate scientific research by automating hypothesis generation and implementation, a new bottleneck emerges: evaluating and filtering hundreds of AI-generated ideas without exhaustive experimentation. We ask whether…

Machine Learning · Computer Science 2026-05-22 Srujan P Mule , Aniketh Garikaparthi , Manasi Patwardhan

Large language models (LLMs) exhibit exceptional performance across various downstream tasks. However, they encounter limitations due to slow inference speeds stemming from their extensive parameters. The early exit (EE) is an approach that…

Computation and Language · Computer Science 2024-12-03 Weiqiao Shan , Long Meng , Tong Zheng , Yingfeng Luo , Bei Li , junxin Wang , Tong Xiao , Jingbo Zhu

Speculative decoding has demonstrated its effectiveness in accelerating the inference of large language models while maintaining a consistent sampling distribution. However, the conventional approach of training a separate draft model to…

Computation and Language · Computer Science 2024-04-30 Fangcheng Liu , Yehui Tang , Zhenhua Liu , Yunsheng Ni , Kai Han , Yunhe Wang

LLM agents that store knowledge as natural language suffer steep retrieval degradation as condition count grows, often struggle to compose learned rules reliably, and typically lack explicit mechanisms to detect stale or adversarial…

Artificial Intelligence · Computer Science 2026-03-11 Arash Shahmansoori

The text generated by large language models is commonly controlled by prompting, where a prompt prepended to a user's query guides the model's output. The prompts used by companies to guide their models are often treated as secrets, to be…

Computation and Language · Computer Science 2024-08-09 Yiming Zhang , Nicholas Carlini , Daphne Ippolito

Modern predictive models are often deployed to environments in which computational budgets are dynamic. Anytime algorithms are well-suited to such environments as, at any point during computation, they can output a prediction whose quality…

Machine Learning · Computer Science 2023-10-31 Metod Jazbec , James Urquhart Allingham , Dan Zhang , Eric Nalisnick

Large reasoning models (LRMs) often generate extensive chain-of-thought (CoT) traces before producing a final answer. As explicit textual artifacts, these traces can be passed to other models to solve the same task, enabling cross-model…

Computation and Language · Computer Science 2026-05-29 Xinyuan Cheng , Beiduo Chen , Philipp Mondorf , Barbara Plank

Standard chain-of-thought reasoning generates a solution in a single forward pass, committing irrevocably to each token and lacking a mechanism to recover from early errors. We introduce Inference-Time Rethinking, a generative framework…

Computation and Language · Computer Science 2026-02-09 Deqian Kong , Minglu Zhao , Aoyang Qin , Bo Pang , Chenxin Tao , David Hartmann , Edouardo Honig , Dehong Xu , Amit Kumar , Matt Sarte , Chuan Li , Jianwen Xie , Ying Nian Wu

Existing dialog datasets contain a sequence of utterances and responses without any explicit background knowledge associated with them. This has resulted in the development of models which treat conversation as a sequence-to-sequence…

Computation and Language · Computer Science 2018-09-24 Nikita Moghe , Siddhartha Arora , Suman Banerjee , Mitesh M. Khapra

Final outputs hide when a checkpoint commits to its next-token prediction. We introduce the convergence gap, a model-diffing diagnostic that decodes each layer's next-token distribution and measures its distance to the model's own final…

Machine Learning · Computer Science 2026-05-11 Yifan Zhou

Chain-of-thought reasoning has driven striking advances in language model capability, yet every reasoning step grows the KV cache, creating a bottleneck to scaling this paradigm further. Current approaches manage these constraints on the…

Machine Learning · Computer Science 2026-04-21 Michael Y. Li , Jubayer Ibn Hamid , Emily B. Fox , Noah D. Goodman

When writing and talking, people sometimes pause to think. Although reasoning-focused works have often framed reasoning as a method of answering questions or completing agentic tasks, reasoning is implicit in almost all written text. For…

Computation and Language · Computer Science 2024-03-19 Eric Zelikman , Georges Harik , Yijia Shao , Varuna Jayasiri , Nick Haber , Noah D. Goodman

Language models retain a significant amount of world knowledge from their pre-training stage. This allows knowledgeable models to be applied to knowledge-intensive tasks prevalent in information retrieval, such as ranking or question…

Computation and Language · Computer Science 2023-06-13 Jonas Wallat , Tianyi Zhang , Avishek Anand

In recent years, deep learning-based single-channel speech separation has improved considerably, in large part driven by increasingly compute- and parameter-efficient neural network architectures. Most such architectures are, however,…