Latent Logic Tree Extraction for Event Sequence Explanation from LLMs
- URL: http://arxiv.org/abs/2406.01124v3
- Date: Fri, 28 Jun 2024 07:54:19 GMT
- Title: Latent Logic Tree Extraction for Event Sequence Explanation from LLMs
- Authors: Zitao Song, Chao Yang, Chaojie Wang, Bo An, Shuang Li,
- Abstract summary: Modern high-stakes systems, such as healthcare or robotics, often generate vast streaming event sequences.
Our goal is to design an efficient, plug-and-play tool to elicit logic tree-based explanations from Large Language Models (LLMs) to provide customized insights into each observed event sequence.
In the online setting, our locally built, lightweight model will iteratively extract the most relevant rules from LLMs for each sequence using only a few iterations.
- Score: 19.90330712436838
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Modern high-stakes systems, such as healthcare or robotics, often generate vast streaming event sequences. Our goal is to design an efficient, plug-and-play tool to elicit logic tree-based explanations from Large Language Models (LLMs) to provide customized insights into each observed event sequence. Built on the temporal point process model for events, our method employs the likelihood function as a score to evaluate generated logic trees. We propose an amortized Expectation-Maximization (EM) learning framework and treat the logic tree as latent variables. In the E-step, we evaluate the posterior distribution over the latent logic trees using an LLM prior and the likelihood of the observed event sequences. LLM provides a high-quality prior for the latent logic trees, however, since the posterior is built over a discrete combinatorial space, we cannot get the closed-form solution. We propose to generate logic tree samples from the posterior using a learnable GFlowNet, which is a diversity-seeking generator for structured discrete variables. The M-step employs the generated logic rules to approximate marginalization over the posterior, facilitating the learning of model parameters and refining the tunable LLM prior parameters. In the online setting, our locally built, lightweight model will iteratively extract the most relevant rules from LLMs for each sequence using only a few iterations. Empirical demonstrations showcase the promising performance and adaptability of our framework.
Related papers
- Graph-Structured Speculative Decoding [52.94367724136063]
Speculative decoding has emerged as a promising technique to accelerate the inference of Large Language Models.
We introduce an innovative approach utilizing a directed acyclic graph (DAG) to manage the drafted hypotheses.
We observe a remarkable speedup of 1.73$times$ to 1.96$times$, significantly surpassing standard speculative decoding.
arXiv Detail & Related papers (2024-07-23T06:21:24Z) - Optimization-based Structural Pruning for Large Language Models without Back-Propagation [57.9629676017527]
We propose an optimization-based structural pruning on Large-Language Models (LLMs)
Our method learns the pruning masks in a probabilistic space directly by optimizing the loss of the pruned model.
Our method operates for 2.7 hours with around 35GB memory for the 13B models on a single A100 GPU, and our pruned models outperform the state-of-the-arts w.r.t. perplexity.
arXiv Detail & Related papers (2024-06-15T09:31:03Z) - Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning [53.241569810013836]
We propose a new framework based on large language models (LLMs) and decision Tree reasoning (OCTree)
Our key idea is to leverage LLMs' reasoning capabilities to find good feature generation rules without manually specifying the search space.
Our empirical results demonstrate that this simple framework consistently enhances the performance of various prediction models.
arXiv Detail & Related papers (2024-06-12T08:31:34Z) - An efficient solution to Hidden Markov Models on trees with coupled branches [0.0]
We extend the framework of Hidden Models (HMMs) on trees to address scenarios where the tree-like structure of the data includes coupled branches.
We develop a programming algorithm that efficiently solves the likelihood, decoding, and parameter learning problems for tree-based HMMs with coupled branches.
arXiv Detail & Related papers (2024-06-03T18:00:00Z) - Recursive Speculative Decoding: Accelerating LLM Inference via Sampling
Without Replacement [11.91629418177851]
Speculative decoding is an inference-accel method for large language models.
Recent works have advanced this method by establishing a draft-token tree.
We present Recursive Speculative Decoding (RSD), a novel tree-based method that samples draft tokens without replacement.
arXiv Detail & Related papers (2024-02-21T22:57:49Z) - Tree-Planner: Efficient Close-loop Task Planning with Large Language Models [63.06270302774049]
Tree-Planner reframes task planning with Large Language Models into three distinct phases.
Tree-Planner achieves state-of-the-art performance while maintaining high efficiency.
arXiv Detail & Related papers (2023-10-12T17:59:50Z) - Amortizing intractable inference in large language models [56.92471123778389]
We use amortized Bayesian inference to sample from intractable posterior distributions.
We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training.
As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem.
arXiv Detail & Related papers (2023-10-06T16:36:08Z) - SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification [13.174386920965107]
SpecInfer is a system that accelerates generative large language model (LLM) serving with tree-based speculative inference and verification.
The correctness of all candidate token sequences represented by a token tree is verified against the LLM in parallel using a novel tree-based parallel decoding mechanism.
arXiv Detail & Related papers (2023-05-16T20:12:59Z) - GFlowNet-EM for learning compositional latent variable models [115.96660869630227]
A key tradeoff in modeling the posteriors over latents is between expressivity and tractable optimization.
We propose the use of GFlowNets, algorithms for sampling from an unnormalized density.
By training GFlowNets to sample from the posterior over latents, we take advantage of their strengths as amortized variational algorithms.
arXiv Detail & Related papers (2023-02-13T18:24:21Z) - A constrained recursion algorithm for batch normalization of
tree-sturctured LSTM [0.29008108937701327]
Tree-structured LSTM is promising way to consider long-distance interaction over hierarchies.
Proposal method is effective for hyper parameter tuning such as the number of batches.
arXiv Detail & Related papers (2020-08-21T10:31:45Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.