mlsanityData to 7 Oct 2026

Word Salad Chopper: Reasoning Models Waste A Ton Of Decoding Budget On Useless Repetitions, Self-Knowingly

arXiv 2511.00536 ↗First posted 1 Nov 2025cs.CLcited by 3

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Large Reasoning Models (LRMs) are often bottlenecked by the high cost of output tokens. We show that a significant portion of these tokens are useless self-repetitions - what we call "word salad" - that exhaust the decoding budget without adding value. Interestingly, we observe that LRMs are self-aware when trapped in these loops: the hidden states of <nn> tokens trailing each reasoning chunk exhibit patterns that allow us to detect word salad behavior on-the-fly via a single-layer linear classifier. Once detected, a simple chop appended by a straightforward regeneration prompt yields substantial length savings with minimal quality loss. Our work offers WordSaladChopper (WSC) - a lightweight, turnkey component for LRM that is minimally invasive to its reasoning trajectory by only removing semantically redundant tokens. Given its low overhead, strong savings, and the lack of semantic value of word salad tokens, we believe it is not too far-fetched to argue that WSC - or a similar component - is a must-have for all LRM applications with user experience in mind. Our code is publicly available at https://github.com/wenyaxie023/WordSaladChopper.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 23 of its 32 references that are in the map. First posted on arXiv 1 Nov 2025.

Builds on

23 of 32 references.

Closest ancestors · 15

Same direction, newest first

  1. 2025Inverse Scaling in Test-Time Compute19 Jul
  2. 2025Dynamic Early Exit in Reasoning Models22 Apr
  3. 2025Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification7 Apr
  4. 2025ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning2 Apr
  5. 2025Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models31 Mar
  6. 2025Efficient Inference for Large Reasoning Models: A Survey29 Mar
  7. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models20 Mar
  8. 2025InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models9 Mar
  9. 2025L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning6 Mar
  10. 2025Self-Training Elicits Concise Reasoning in Large Language Models27 Feb
  11. 2025TokenSkip: Controllable Chain-of-Thought Compression in LLMs17 Feb
  12. 2025Demystifying Long Chain-of-Thought Reasoning in LLMs5 Feb
3 more
  1. 2025s1: Simple test-time scaling31 Jan
  2. 2025Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs30 Jan
  3. 2024Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost29 Jul

Other references · 8

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2025Qwen3 Technical Reportcited by 8,195
  3. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 763
  4. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  5. 2025Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketchingcited by 116
  6. 2025Small Models Struggle to Learn from Strong Reasonerscited by 109
  7. 2025Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoningcited by 101
  8. 2025Repetitions are not all alike: distinct mechanisms sustain repetition in language modelscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Circular Reasoning: Understanding Self-Reinforcing Loops in Large Reasoning Modelscited by 5
  2. 2026Resource Consumption Threats in Large Language Modelscited by 2
  3. 2026LatentSift: Policy-State Filtering for Token-Efficient Verification of Software Engineering Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Think Twice Before You Write -- an Entropy-based Decoding Strategy to Enhance LLM Reasoning
  2. 2026Thinking Before Constraining: A Unified Decoding Framework for Large Language Models
  3. 2026Shorthand for Thought: Compressing LLM Reasoning via Entropy-Guided Supertokens
  4. 2026Self-Speculation for Faster Reasoning Models
  5. 2025SplitReason: Learning To Offload Reasoning
  6. 2026Wrong Prediction, Right Answer: Recovering Evidence from Collapsed LLM Sequence Scores
  7. 2025Logic Haystacks: Probing LLMs Long-Context Logical Reasoning (Without Easily Identifiable Unrelated Padding)
  8. 2026BLADE: Boundary-Expanded and Layer-Adaptive Dynamic Exit for Efficient LLM Reasoning