Copertina

Do Cognitively Interpretable Reasoning Traces Improve LLM Performance?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Bhambri, Siddhant, Biswas, Upasana, Kambhampati, Subbarao
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation
di: Bhambri, Siddhant, et al.
Pubblicazione: (2025)

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

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

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

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

Can Large Language Models Reason and Plan?
di: Kambhampati, Subbarao
Pubblicazione: (2024)

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

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

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

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

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

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

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

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

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

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

Improving LLM Reasoning through Interpretable Role-Playing Steering
di: Wang, Anyi, et al.
Pubblicazione: (2025)

ReasonOps: Operator Segmentation for LLM Reasoning Traces
di: Lee, Daniel, et al.
Pubblicazione: (2026)

On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks
di: Stechly, Kaya, et al.
Pubblicazione: (2024)

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

Cognitive BASIC: An In-Model Interpreted Reasoning Language for LLMs
di: Kramer, Oliver
Pubblicazione: (2025)

InFact: Informativeness Alignment for Improved LLM Factuality
di: Cohen, Roi, et al.
Pubblicazione: (2025)

How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative Reasoning
di: Chen, Haoyang, et al.
Pubblicazione: (2026)

Follow the Path: Reasoning over Knowledge Graph Paths to Improve Large Language Model Factuality
di: Zhang, Mike, et al.
Pubblicazione: (2025)

Improving Large Language Model (LLM) fidelity through context-aware grounding: A systematic approach to reliability and veracity
di: Talukdar, Wrick, et al.
Pubblicazione: (2024)

Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
di: Huan, Maggie, et al.
Pubblicazione: (2025)

Spot the BlindSpots: Systematic Identification and Quantification of Fine-Grained LLM Biases in Contact Center Summaries
di: Mayilvaghanan, Kawin, et al.
Pubblicazione: (2025)

How Do LLMs Perform Two-Hop Reasoning in Context?
di: Guo, Tianyu, et al.
Pubblicazione: (2025)

Two-Stage Reasoning-Infused Learning: Improving Classification with LLM-Generated Reasoning
di: Henrichsen, Mads, et al.
Pubblicazione: (2025)

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

Planning in Strawberry Fields: Evaluating and Improving the Planning and Scheduling Capabilities of LRM o1
di: Valmeekam, Karthik, et al.
Pubblicazione: (2024)

Performative Thinking? The Brittle Correlation Between CoT Length and Problem Complexity
di: Palod, Vardhan, et al.
Pubblicazione: (2025)

Tracing Thought: Using Chain-of-Thought Reasoning to Identify the LLM Behind AI-Generated Text
di: Agrahari, Shifali, et al.
Pubblicazione: (2025)

RAG over Thinking Traces Can Improve Reasoning Tasks
di: Arabzadeh, Negar, et al.
Pubblicazione: (2026)

Entropy-Aware Speculative Decoding Toward Improved LLM Reasoning
di: Su, Tiancheng, et al.
Pubblicazione: (2025)

Sound and Complete Neurosymbolic Reasoning with LLM-Grounded Interpretations
di: Allen, Bradley P., et al.
Pubblicazione: (2025)

LLaVul: A Multimodal LLM for Interpretable Vulnerability Reasoning about Source Code
di: Jararweh, Ala, et al.
Pubblicazione: (2025)

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

EmoLLM: Appraisal-Grounded Cognitive-Emotional Co-Reasoning in Large Language Models
di: Zhang, Yifei, et al.
Pubblicazione: (2026)

Do AI Models Perform Human-like Abstract Reasoning Across Modalities?
di: Beger, Claas, et al.
Pubblicazione: (2025)