English
Related papers

Related papers: Mind the Shift: Decoding Monetary Policy Stance fr…

200 papers

Stochastic versions of recursive integrated climate-economy assessment models are essential for studying and quantifying policy decisions under uncertainty. However, as the number of state variables and stochastic shocks increases, solving…

Despite great performance on Olympiad-level reasoning problems, frontier large language models can still struggle on high school math when presented with novel problems outside standard benchmarks. Going beyond final accuracy, we propose a…

Computation and Language · Computer Science 2025-04-10 Atharva Pandey , Kshitij Dubey , Rahul Sharma , Amit Sharma

We introduce a tool for rigorous and automated verification of large language model (LLM)- based policies in memoryless sequential decision-making tasks. Given a Markov decision process (MDP) representing the sequential decision-making…

Artificial Intelligence · Computer Science 2025-10-09 Dennis Gross , Helge Spieker , Arnaud Gotlieb

Recent large language models (LLMs) have shown remarkable performance in aligning generated text with user intentions across various tasks. When it comes to long-form text generation, there has been a growing interest in generation from a…

Computation and Language · Computer Science 2024-04-04 Yinhong Liu , Yixuan Su , Ehsan Shareghi , Nigel Collier

We investigate whether continuous-control policies can be represented and learned as discrete logic circuits instead of continuous neural networks. We introduce Differentiable Weightless Controllers (DWCs), a symbolic-differentiable…

Machine Learning · Computer Science 2025-12-02 Fabian Kresse , Christoph H. Lampert

Large Language Models inherit stereotypes from their pretraining data, leading to biased behavior toward certain social groups in many Natural Language Processing tasks, such as hateful speech detection or sentiment analysis. Surprisingly,…

Computation and Language · Computer Science 2025-10-24 Anthony Dubreuil , Antoine Gourru , Christine Largeron , Amine Trabelsi

Pre-trained large language models (LMs) struggle to perform logical reasoning reliably despite advances in scale and compositionality. In this work, we tackle this challenge through the lens of symbolic programming. We propose DSR-LM, a…

Artificial Intelligence · Computer Science 2023-05-09 Hanlin Zhang , Jiani Huang , Ziyang Li , Mayur Naik , Eric Xing

Time series forecasting (TSF) is critical across domains such as finance, meteorology, and energy. While extending the lookback window theoretically provides richer historical context, in practice, it often introduces irrelevant noise and…

Machine Learning · Computer Science 2026-04-03 Xiang Ao , Yinyu Tan , Mengru Chen

Instruction-tuned language models increasingly rely on large multi-turn dialogue corpora, but these datasets are often noisy and structurally inconsistent, with topic drift, repetitive chitchat, and mismatched answer formats across turns.…

Computation and Language · Computer Science 2026-04-21 Bo Li , Shikun Zhang , Wei Ye

Should we trust Large Language Models (LLMs) with high accuracy? LLMs achieve high accuracy on reasoning benchmarks, but correctness alone does not reveal the quality of the reasoning used to produce it. This highlights a fundamental…

Computation and Language · Computer Science 2026-04-15 Manas Pathak , Xingyao Chen , Shuozhe Li , Amy Zhang , Liu Leqi

Sequence-level evaluations in autoregressive Large Language Models (LLMs) rely on highly dependent token generation. Establishing tight concentration bounds for these processes remains a challenge due to two fundamental bottlenecks in…

Machine Learning · Computer Science 2026-05-19 Pei-Sen Li

Political polarization emerges from a complex interplay of beliefs about policies, figures, and issues. However, most computational analyses reduce discourse to coarse partisan labels, overlooking how these beliefs interact. This is…

Computation and Language · Computer Science 2026-05-21 Özgür Togay , Javier Garcia-Bernardo , Florian Kunneman , Anastasia Giachanou

Self-consistency (SC) is a widely used test-time inference technique for improving performance in chain-of-thought reasoning. It involves generating multiple responses, or samples from a large language model (LLM) and selecting the most…

Machine Learning · Computer Science 2025-11-18 Austin Feng , Marius Alonso , Ambroise Odonnat

Stochastic sampling strategies such as top-k and top-p have been widely used in dialogue generation task. However, as an open-domain chatting system, there will be two different conversation scenarios, i.e. chit-chat and knowledge-based…

Computation and Language · Computer Science 2024-06-13 Yiwei Li , Fei Mi , Yitong Li , Yasheng Wang , Bin Sun , Shaoxiong Feng , Kan Li

Masked diffusion models (MDMs) have recently emerged as a novel framework for language modeling. MDMs generate sentences by iteratively denoising masked sequences, filling in [MASK] tokens step by step. Although MDMs support any-order…

Machine Learning · Computer Science 2026-02-27 Chunsan Hong , Seonho An , Min-Soo Kim , Jong Chul Ye

Large Language Models (LLMs) increasingly shape global discourse, making fairness and ideological neutrality essential for responsible AI deployment. Despite growing attention to political bias in LLMs, prior work largely focuses on…

Computation and Language · Computer Science 2026-02-12 Afrozah Nadeem , Agrima Seth , Mehwish Nasim , Usman Naseem

As large language models (LLMs) are increasingly deployed, understanding how they express political positioning is important for evaluating alignment and downstream effects. We audit 26 contemporary LLMs using three political psychometric…

Computers and Society · Computer Science 2026-03-18 Adib Sakhawat , Tahsin Islam , Takia Farhin , Syed Rifat Raiyan , Hasan Mahmud , Md Kamrul Hasan

Post-training of large language models is essential for adapting pre-trained language models (PLMs) to align with human preferences and downstream tasks. While PLMs typically exhibit well-calibrated confidence, post-trained language models…

Machine Learning · Computer Science 2025-11-26 Beier Luo , Shuoyuan Wang , Sharon Li , Hongxin Wei

Language-conditioned manipulation policies typically process instructions and observations through shared network parameters. This task-state entanglement provides a pathway for observation leakage -- networks learn scene-to-action…

Robotics · Computer Science 2026-05-21 Hanxiang Ren , Pei Zhou , Xunzhe Zhou , Yanchao Yang

Central banks cannot observe market reactions to their communications before release. We propose a framework in which Large Language Models simulate 30 heterogeneous traders interpreting European Central Bank press conference transcripts,…

General Economics · Economics 2026-05-19 Umberto Collodel