REVIEW 5 cited by
Understanding and Patching Compositional Reasoning in LLMs
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
LLMs have marked a revolutonary shift, yet they falter when faced with compositional reasoning tasks. Our research embarks on a quest to uncover the root causes of compositional reasoning failures of LLMs, uncovering that most of them stem from the improperly generated or leveraged implicit reasoning results. Inspired by our empirical findings, we resort to Logit Lens and an intervention experiment to dissect the inner hidden states of LLMs. This deep dive reveals that implicit reasoning results indeed surface within middle layers and play a causative role in shaping the final explicit reasoning results. Our exploration further locates multi-head self-attention (MHSA) modules within these layers, which emerge as the linchpins in accurate generation and leveraing of implicit reasoning results. Grounded on the above findings, we develop CREME, a lightweight method to patch errors in compositional reasoning via editing the located MHSA modules. Our empirical evidence stands testament to CREME's effectiveness, paving the way for autonomously and continuously enhancing compositional reasoning capabilities in language models.
Forward citations
Cited by 5 Pith papers
-
Verbalizable Representations Form a Global Workspace in Language Models
Language models represent their current reasoning in a small, readable set of verbalizable vectors (the J-space) that functions like a global workspace.
-
The Power of Power Law: Asymmetry Enables Compositional Reasoning
Power-law data sampling creates beneficial asymmetry in the loss landscape that lets models acquire high-frequency skill compositions first, enabling more efficient learning of rare long-tail skills than uniform distr...
-
When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inference
TSAIA, a new benchmark, tests eight LLMs on 1,054 multi-step time series tasks and finds they cannot reliably complete the required workflows.
-
A Survey on Latent Reasoning
A survey that organizes latent reasoning methods into vertical recurrence, horizontal recurrence, and infinite-depth diffusion, arguing that silent reasoning can beat explicit chain-of-thought.
-
CryptoX : Compositional Reasoning Evaluation of Large Language Models
A benchmark that encodes prompts in secret codes and measures how much accuracy models lose, showing most LLMs, especially open-source ones, struggle on this two-step compositional task.
Discussion (0). Continue with ORCID to comment.