Challenge: Large language models exhibit high-level commonsense reasoning abilities, especially with enhancement methods like Chain-of-Thought (CoT).
Approach: They propose a chain-of-thought-like method to elicit models' potential abilities to generate rationales and answers that are based on attribution tracing and causal tracers to probe the internal working mechanism of the LLM.
Outcome: The proposed method eliminates Toxic CoT problems and improves the model’s overall commonsense reasoning performance by 5.5%.

Similar Papers

Generating Effective CoT Traces for Mitigating Causal Hallucination (2026.findings-acl)

Copied to clipboard

Challenge: Large language models suffer from severe causal hallucination in event causality identification (ECI) there is currently no metric for quantifying causal hallucinonation for small models .
Approach: They propose to fine-tune large language models with Chain-of-Thought (CoT) traces to mitigate hallucination in smaller models by introducing a new metric, the Causal Hallucinations Rate, which quantifies hallucinosity.
Outcome: The proposed pipeline reduces causal hallucination in smaller models and improves mean accuracy under intentionally misleading intervention prompts.
How Chain-of-Thought Works? Tracing Information Flow from Decoding, Projection, and Activation (2026.findings-acl)

Copied to clipboard

Challenge: Chain-of-Thought (CoT) prompting significantly enhances model reasoning, yet its internal mechanisms remain poorly understood.
Approach: They reversely traced information flow across decoding, projection, and activation phases and found that CoT may serve as a decoding space pruner .
Outcome: The proposed framework can be used to design more efficient and robust prompts.
CAC-CoT: Connector-Aware Compact Chain-of-Thought for Efficient Reasoning Data Synthesis Across Dual-System Cognitive Tasks (2025.findings-emnlp)

Copied to clipboard

Challenge: Long chain-of-thought (CoT) prompting often slows or even degrades performance on fast, intuitive "System-1" tasks.
Approach: They introduce a method that deliberately restricts reasoning to a small, fixed set of connector phrases, steering the model toward concise and well-structured explanations.
Outcome: The method achieves 85% on GSM8K and 40% on GPQA while also surpassing the baseline by over 20%.
How Likely Do LLMs with CoT Mimic Human Reasoning? (2025.coling-main)

Copied to clipboard

Challenge: Using chain-of-thought to elicit reasoning capabilities is not always effective and accurate.
Approach: They compare the reasoning process of LLMs with humans to understand the causal chain . they find that LLM deviates from the ideal causal chain, resulting in spurious correlations .
Outcome: The proposed method does not improve performance or accurately represent reasoning processes in LLMs.
Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation (2026.acl-long)

Copied to clipboard

Challenge: Recent advances in reasoning-oriented Large Language Models have been driven by the introduction of Chain-of-Thought (CoT) traces.
Approach: They propose to use CoT traces to guide model inference and serve as supervision signals for Knowledge Distillation to improve smaller models.
Outcome: The proposed model is based on a rule-based problem decomposition method and is valid for both semantic correctness and interpretability to the end user.
Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens (2026.findings-acl)

Copied to clipboard

Challenge: Chain-of-Thought (CoT) prompting has been shown to be effective in eliciting structured reasoning from large language models (LLMs).
Approach: They propose a data distribution lens to understand when and why CoT reasoning fails . they propose 'data-based' training that trains LLMs from scratch .
Outcome: The proposed model enables models to generate reasoning trajectories that approximate those observed during training.
On Second Thought, Let’s Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning (2023.acl-long)

Copied to clipboard

Challenge: Prior work has focused on logical reasoning tasks; it remains unclear whether improvements hold for more diverse types of reasoning, especially in socially situated contexts.
Approach: They perform a controlled evaluation of zero-shot CoT reasoning in two socially sensitive domains: harmful questions and stereotype benchmarks.
Outcome: The results show that zero-shot CoT reasoning increases model’s likelihood to produce harmful or undesirable output, but decreases with improved instruction following.
Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking? (2025.findings-acl)

Copied to clipboard

Challenge: Existing jailbreak attacks fail against reasoning models enhanced by Chain-of-Thought (CoT) reasoning.
Approach: They propose a jailbreak method that uses Chain-of-Thought reasoning to reduce harmfulness from jailbreaking.
Outcome: The proposed jailbreak method performs well against open AI models and deepseek-R1 reasoning models.
Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression (2026.acl-long)

Copied to clipboard

Challenge: Existing work on reducing CoT generation in reasoning impairs the necessary information for deriving the correct answer.
Approach: They propose a reasoning paradigm that takes CoT as a part of context to simplify the reasoning task for Large Language Models (LLMs).
Outcome: The proposed framework reduces the generation length of LLMs, but its effectiveness hinges on the efficiency and reliability of the contextual CoT generation.
Your Reasoning Model Knows What Counts: Self-Guided Chain-of-Thought Pruning for Efficient Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to Chain-of-Thought reasoning are often degraded because they disregard the model’s intrinsic reasoning dependency.
Approach: They propose a self-guided pruning framework that leverages the model’s intrinsic likelihood landscape to identify segments that are extraneous to its specific reasoning pattern.
Outcome: The proposed framework reduces output length while maintaining or improving accuracy on multiple benchmarks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations