Cover Image

Lexical Hints of Accuracy in LLM Reasoning Chains

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Vanhoyweghen, Arne, Verbeken, Brecht, Algaba, Andres, Ginis, Vincent
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Benchmarks Saturate When The Model Gets Smarter Than The Judge
by: Ballon, Marthe, et al.
Published: (2026)

Probing the Trajectories of Reasoning Traces in Large Language Models
by: Ballon, Marthe, et al.
Published: (2026)

Metro 3 in Brussels under uncertainty: scenario-based public transport accessibility analysis
by: Verbeken, Brecht, et al.
Published: (2025)

Estimating problem difficulty without ground truth using Large Language Model comparisons
by: Ballon, Marthe, et al.
Published: (2025)

Early Evidence of Vibe-Proving with Consumer LLMs: A Case Study on Spectral Region Characterization with ChatGPT-5.2 (Thinking)
by: Verbeken, Brecht, et al.
Published: (2026)

Model-Agnostic Solutions for Deep Reinforcement Learning in Non-Ergodic Contexts
by: Verbruggen, Bert, et al.
Published: (2026)

How Deep Do Large Language Models Internalize Scientific Literature and Citation Practices?
by: Algaba, Andres, et al.
Published: (2025)

The Relationship Between Reasoning and Performance in Large Language Models -- o3 (mini) Thinks Harder, Not Longer
by: Ballon, Marthe, et al.
Published: (2025)

Scalable Classification of Course Information Sheets Using Large Language Models: A Reusable Institutional Method for Academic Quality Assurance
by: Verbeken, Brecht, et al.
Published: (2026)

Structurally Human, Semantically Biased: Detecting LLM-Generated References with Embeddings and GNNs
by: Mobini, Melika, et al.
Published: (2026)

Human-in-the-Loop LLM Grading for Handwritten Mathematics Assessments
by: Vanhoyweghen, Arne, et al.
Published: (2026)

StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason
by: Zhang, Kaiyi, et al.
Published: (2025)

Progressive-Hint Prompting Improves Reasoning in Large Language Models
by: Zheng, Chuanyang, et al.
Published: (2023)

Flexible Counterfactual Explanations with Generative Models
by: Hellemans, Stig, et al.
Published: (2025)

Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization
by: Zaman, Kerem, et al.
Published: (2025)

Probabilistic Soundness Guarantees in LLM Reasoning Chains
by: You, Weiqiu, et al.
Published: (2025)

Unspoken Hints: Accuracy Without Acknowledgement in LLM Reasoning
by: Marioriyad, Arash, et al.
Published: (2025)

Ergodicity in reinforcement learning
by: Baumann, Dominik, et al.
Published: (2026)

On Lexical Invariance on Multisets and Graphs
by: Zhang, Muhan
Published: (2024)

Learning to Hint for Reinforcement Learning
by: Xia, Yu, et al.
Published: (2026)

Chain-of-Thought Unfaithfulness as Disguised Accuracy
by: Bentham, Oliver, et al.
Published: (2024)

Mitigating Distribution Sharpening in Math RLVR via Distribution-Aligned Hint Synthesis and Backward Hint Annealing
by: Xie, Pei-Xi, et al.
Published: (2026)

Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs
by: Zhang, Xuan, et al.
Published: (2024)

Think-Augmented Function Calling: Improving LLM Parameter Accuracy Through Embedded Reasoning
by: Wei, Lei, et al.
Published: (2026)

Luxical: High-Speed Lexical-Dense Text Embeddings
by: DatologyAI, et al.
Published: (2025)

Demystifying Long Chain-of-Thought Reasoning in LLMs
by: Yeo, Edward, et al.
Published: (2025)

Understanding Hidden Computations in Chain-of-Thought Reasoning
by: Bharadwaj, Aryasomayajula Ram
Published: (2024)

From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
by: Jiang, Xitai, et al.
Published: (2026)

Self-Hinting Language Models Enhance Reinforcement Learning
by: Liao, Baohao, et al.
Published: (2026)

Exploring Chain-of-Thought Reasoning for Steerable Pluralistic Alignment
by: Zhang, Yunfan, et al.
Published: (2025)

Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning
by: Gu, Yu, et al.
Published: (2026)

Two Calls, Two Moments, and the Vote-Accuracy Curve of Repeated LLM Inference
by: Liu, Yi
Published: (2026)

Nudging the Boundaries of LLM Reasoning
by: Chen, Justin Chih-Yao, et al.
Published: (2025)

Neural Recovery of Historical Lexical Structure in Bantu Languages from Modern Data
by: Mutisya, Hillary, et al.
Published: (2026)

Lexical Tone is Hard to Quantize: Probing Discrete Speech Units in Mandarin and Yorùbá
by: Osakuade, Opeyemi, et al.
Published: (2026)

Meta-Tuning LLMs to Leverage Lexical Knowledge for Generalizable Language Style Understanding
by: Guo, Ruohao, et al.
Published: (2023)

Dissecting Long-Chain-of-Thought Reasoning Models: An Empirical Study
by: Mu, Yongyu, et al.
Published: (2025)

Large Language Models Reflect Human Citation Patterns with a Heightened Citation Bias
by: Algaba, Andres, et al.
Published: (2024)

Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoning
by: Ye, Ruimeng, et al.
Published: (2024)

Fractured Chain-of-Thought Reasoning
by: Liao, Baohao, et al.
Published: (2025)