Cover Image

Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bhambri, Siddhant, Biswas, Upasana, Kambhampati, Subbarao
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Do Cognitively Interpretable Reasoning Traces Improve LLM Performance?
by: Bhambri, Siddhant, et al.
Published: (2025)

On the Brittle Foundations of ReAct Prompting for Agentic Large Language Models
by: Verma, Mudit, et al.
Published: (2024)

Who is Helping Whom? Analyzing Inter-dependencies to Evaluate Cooperation in Human-AI Teaming
by: Biswas, Upasana, et al.
Published: (2025)

Incorporating Human Flexibility through Reward Preferences in Human-AI Teaming
by: Bhambri, Siddhant, et al.
Published: (2023)

Theory of Mind abilities of Large Language Models in Human-Robot Interaction : An Illusion?
by: Verma, Mudit, et al.
Published: (2024)

Local Coherence or Global Validity? Investigating RLVR Traces in Math Domains
by: Samineni, Soumya Rani, et al.
Published: (2025)

Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!
by: Kambhampati, Subbarao, et al.
Published: (2025)

Can Large Language Models Reason and Plan?
by: Kambhampati, Subbarao
Published: (2024)

Algorithmic Language Models with Neurally Compiled Libraries
by: Saldyt, Lucas, et al.
Published: (2024)

LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench
by: Valmeekam, Karthik, et al.
Published: (2024)

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition
by: McDonald, Tyler, et al.
Published: (2025)

Robust Planning with LLM-Modulo Framework: Case Study in Travel Planning
by: Gundawar, Atharva, et al.
Published: (2024)

Robust Planning with Compound LLM Architectures: An LLM-Modulo Approach
by: Gundawar, Atharva, et al.
Published: (2024)

MERIT: Memory-Enhanced Retrieval for Interpretable Knowledge Tracing
by: Li, Runze, et al.
Published: (2026)

Extracting Heuristics from Large Language Models for Reward Shaping in Reinforcement Learning
by: Bhambri, Siddhant, et al.
Published: (2024)

Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues
by: Huang, Shuyan, et al.
Published: (2026)

Evaluating the False Trust Engendered by LLM Explanations
by: Palod, Vardhan, et al.
Published: (2026)

KnowTrace: Bootstrapping Iterative Retrieval-Augmented Generation with Structured Knowledge Tracing
by: Li, Rui, et al.
Published: (2025)

The Knowledge-Behaviour Disconnect in LLM-based Chatbots
by: Broersen, Jan
Published: (2025)

Explainable Few-shot Knowledge Tracing
by: Li, Haoxuan, et al.
Published: (2024)

Automated Knowledge Component Generation for Interpretable Knowledge Tracing in Coding Problems
by: Duan, Zhangqi, et al.
Published: (2025)

Protecting Language Models Against Unauthorized Distillation through Trace Rewriting
by: Ma, Xinhang, et al.
Published: (2026)

Intrinsic Test of Unlearning Using Parametric Knowledge Traces
by: Hong, Yihuai, et al.
Published: (2024)

LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks
by: Kambhampati, Subbarao, et al.
Published: (2024)

Contrastive Cross-Course Knowledge Tracing via Concept Graph Guided Knowledge Transfer
by: Han, Wenkang, et al.
Published: (2025)

Faster, Cheaper, More Accurate: Specialised Knowledge Tracing Models Outperform LLMs
by: Bhattacharyya, Prarthana, et al.
Published: (2026)

Tracing the Roots of Facts in Multilingual Language Models: Independent, Shared, and Transferred Knowledge
by: Zhao, Xin, et al.
Published: (2024)

TraceCoder: Towards Traceable ICD Coding via Multi-Source Knowledge Integration
by: Ren, Mucheng, et al.
Published: (2025)

Next Token Knowledge Tracing: Exploiting Pretrained LLM Representations to Decode Student Behaviour
by: Norris, Max, et al.
Published: (2025)

Behavior-Aware Item Modeling via Dynamic Procedural Solution Representations for Knowledge Tracing
by: Seo, Jun, et al.
Published: (2026)

Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
by: Chen, Jianhui, et al.
Published: (2026)

TraceSIR: A Multi-Agent Framework for Structured Analysis and Reporting of Agentic Execution Traces
by: Yang, Shu-Xun, et al.
Published: (2026)

PICKT: Practical Interlinked Concept Knowledge Tracing for Personalized Learning using Knowledge Map Concept Relations
by: Lee, Wonbeen, et al.
Published: (2025)

Mind The Gap: Quantifying Mechanistic Gaps in Algorithmic Reasoning via Neural Compilation
by: Saldyt, Lucas, et al.
Published: (2025)

Trace and Edit Relation Associations in GPT
by: Li, Jiahang, et al.
Published: (2023)

LLM-KT: Aligning Large Language Models with Knowledge Tracing using a Plug-and-Play Instruction
by: Wang, Ziwei, et al.
Published: (2025)

Revisiting the UID Hypothesis in LLM Reasoning Traces
by: Gwak, Minju, et al.
Published: (2025)

TRAIL: Trace Reasoning and Agentic Issue Localization
by: Deshpande, Darshan, et al.
Published: (2025)

CLST: Cold-Start Mitigation in Knowledge Tracing by Aligning a Generative Language Model as a Students' Knowledge Tracer
by: Jung, Heeseok, et al.
Published: (2024)

FASTTRACK: Fast and Accurate Fact Tracing for LLMs
by: Chen, Si, et al.
Published: (2024)