Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Bhambri, Siddhant, Biswas, Upasana, Kambhampati, Subbarao
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Do Cognitively Interpretable Reasoning Traces Improve LLM Performance?
par: Bhambri, Siddhant, et autres
Publié: (2025)

On the Brittle Foundations of ReAct Prompting for Agentic Large Language Models
par: Verma, Mudit, et autres
Publié: (2024)

Who is Helping Whom? Analyzing Inter-dependencies to Evaluate Cooperation in Human-AI Teaming
par: Biswas, Upasana, et autres
Publié: (2025)

Incorporating Human Flexibility through Reward Preferences in Human-AI Teaming
par: Bhambri, Siddhant, et autres
Publié: (2023)

Local Coherence or Global Validity? Investigating RLVR Traces in Math Domains
par: Samineni, Soumya Rani, et autres
Publié: (2025)

Theory of Mind abilities of Large Language Models in Human-Robot Interaction : An Illusion?
par: Verma, Mudit, et autres
Publié: (2024)

Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!
par: Kambhampati, Subbarao, et autres
Publié: (2025)

Can Large Language Models Reason and Plan?
par: Kambhampati, Subbarao
Publié: (2024)

Algorithmic Language Models with Neurally Compiled Libraries
par: Saldyt, Lucas, et autres
Publié: (2024)

LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench
par: Valmeekam, Karthik, et autres
Publié: (2024)

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition
par: McDonald, Tyler, et autres
Publié: (2025)

Robust Planning with Compound LLM Architectures: An LLM-Modulo Approach
par: Gundawar, Atharva, et autres
Publié: (2024)

Robust Planning with LLM-Modulo Framework: Case Study in Travel Planning
par: Gundawar, Atharva, et autres
Publié: (2024)

MERIT: Memory-Enhanced Retrieval for Interpretable Knowledge Tracing
par: Li, Runze, et autres
Publié: (2026)

Extracting Heuristics from Large Language Models for Reward Shaping in Reinforcement Learning
par: Bhambri, Siddhant, et autres
Publié: (2024)

Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues
par: Huang, Shuyan, et autres
Publié: (2026)

Evaluating the False Trust Engendered by LLM Explanations
par: Palod, Vardhan, et autres
Publié: (2026)

KnowTrace: Bootstrapping Iterative Retrieval-Augmented Generation with Structured Knowledge Tracing
par: Li, Rui, et autres
Publié: (2025)

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

Explainable Few-shot Knowledge Tracing
par: Li, Haoxuan, et autres
Publié: (2024)

Automated Knowledge Component Generation for Interpretable Knowledge Tracing in Coding Problems
par: Duan, Zhangqi, et autres
Publié: (2025)

Protecting Language Models Against Unauthorized Distillation through Trace Rewriting
par: Ma, Xinhang, et autres
Publié: (2026)

Intrinsic Test of Unlearning Using Parametric Knowledge Traces
par: Hong, Yihuai, et autres
Publié: (2024)

LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks
par: Kambhampati, Subbarao, et autres
Publié: (2024)

Contrastive Cross-Course Knowledge Tracing via Concept Graph Guided Knowledge Transfer
par: Han, Wenkang, et autres
Publié: (2025)

Faster, Cheaper, More Accurate: Specialised Knowledge Tracing Models Outperform LLMs
par: Bhattacharyya, Prarthana, et autres
Publié: (2026)

Tracing the Roots of Facts in Multilingual Language Models: Independent, Shared, and Transferred Knowledge
par: Zhao, Xin, et autres
Publié: (2024)

TraceCoder: Towards Traceable ICD Coding via Multi-Source Knowledge Integration
par: Ren, Mucheng, et autres
Publié: (2025)

Next Token Knowledge Tracing: Exploiting Pretrained LLM Representations to Decode Student Behaviour
par: Norris, Max, et autres
Publié: (2025)

Behavior-Aware Item Modeling via Dynamic Procedural Solution Representations for Knowledge Tracing
par: Seo, Jun, et autres
Publié: (2026)

Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
par: Chen, Jianhui, et autres
Publié: (2026)

TraceSIR: A Multi-Agent Framework for Structured Analysis and Reporting of Agentic Execution Traces
par: Yang, Shu-Xun, et autres
Publié: (2026)

PICKT: Practical Interlinked Concept Knowledge Tracing for Personalized Learning using Knowledge Map Concept Relations
par: Lee, Wonbeen, et autres
Publié: (2025)

Mind The Gap: Quantifying Mechanistic Gaps in Algorithmic Reasoning via Neural Compilation
par: Saldyt, Lucas, et autres
Publié: (2025)

Trace and Edit Relation Associations in GPT
par: Li, Jiahang, et autres
Publié: (2023)

LLM-KT: Aligning Large Language Models with Knowledge Tracing using a Plug-and-Play Instruction
par: Wang, Ziwei, et autres
Publié: (2025)

Revisiting the UID Hypothesis in LLM Reasoning Traces
par: Gwak, Minju, et autres
Publié: (2025)

TRAIL: Trace Reasoning and Agentic Issue Localization
par: Deshpande, Darshan, et autres
Publié: (2025)

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

FASTTRACK: Fast and Accurate Fact Tracing for LLMs
par: Chen, Si, et autres
Publié: (2024)