REVIEW 15 cited by
Making Large Language Models Better Reasoners with Step-Aware Verifier
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
Signed reviews
read the original abstract
Few-shot learning is a challenging task that requires language models to generalize from limited examples. Large language models like GPT-3 and PaLM have made impressive progress in this area, but they still face difficulties in reasoning tasks such as GSM8K, a benchmark for arithmetic problems. To improve their reasoning skills, previous work has proposed to guide the language model with prompts that elicit a series of reasoning steps before giving the final answer, achieving a significant improvement on GSM8K from 17.9% to 58.1% in problem-solving rate. In this paper, we present DIVERSE (Diverse Verifier on Reasoning Step), a novel approach that further enhances the reasoning capability of language models. DIVERSE has three main components: first, it generates diverse prompts to explore different reasoning paths for the same question; second, it uses a verifier to filter out incorrect answers based on a weighted voting scheme; and third, it verifies each reasoning step individually instead of the whole chain. We evaluate DIVERSE on the latest language model code-davinci-002 and show that it achieves new state-of-the-art results on six of eight reasoning benchmarks (e.g., GSM8K 74.4% to 83.2%).
Forward citations
Cited by 15 Pith papers
-
BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation
BARE generates diverse, high-quality synthetic training data from only three seed examples by having a base model draft and an instruction-tuned model refine, improving downstream fine-tuning accuracy in few-shot settings.
-
DIVE: Diversified Iterative Self-Improvement
DIVE combines global sample pooling with diversity-aware data selection to counter output diversity collapse in iterative preference learning for LLMs.
-
B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
B-STaR dynamically tunes sampling temperature and reward thresholds during iterative self-training, improving Pass@1 on math, code, and commonsense reasoning benchmarks versus static self-improvement baselines.
-
Preference Optimization for Reasoning with Pseudo Feedback
Generating pseudo test cases from frontier models or self-consistency and using them as DPO preference signals improves 7B LLMs on math and code benchmarks, sometimes beating 72B models.
-
AUTOLAW: Enhancing Legal Compliance in Large Language Models via Case Law Generation and Jury-Inspired Deliberation
AutoLaw's verifier-ranked legal-role jury with a similar-case demonstration beats majority voting for violation detection on three law and policy benchmarks.
-
MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision
A process reward model trained on 700k automatically generated step-level labels from only 10k seed math problems improves Best-of-N accuracy on multimodal math benchmarks.
-
Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models
Training LLMs to append a <backtrack> token after erroneous reasoning steps and to use that signal at inference time improves Countdown accuracy by more than 40 percent over supervised fine-tuning.
-
Policy Guided Tree Search for Enhanced LLM Reasoning
PGTS trains a graph-transformer policy via PPO to guide tree search over LLM reasoning steps, reporting improved accuracy and lower token use than chain-of-thought and MCTS baselines.
-
CDW-CoT: Clustered Distance-Weighted Chain-of-Thoughts Reasoning
CDW-CoT groups a reasoning dataset into clusters, learns a prompt distribution per cluster, and interpolates these distributions by embedding distance for each new query, reporting higher exact-match accuracy than thr...
-
Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination
VIC improves multimodal LLM accuracy on hallucination and general VQA benchmarks by reasoning from text before seeing the image, though gains are inconsistent on open-source models.
-
Leveraging Large Language Models for Bengali Math Word Problem Solving with Chain of Thought Reasoning
A new Bengali math word problem dataset translated from GSM8K is benchmarked with chain-of-thought prompting, yielding 88% accuracy with LLaMA-3.3 70B on a 1,000-sample test subset.
-
MultiQ&A: An Analysis in Measuring Robustness via Automated Crowdsourcing of Question Perturbations and Answers
MultiQ&A automatically rephrases questions and crowdsources answers from LLM agents, showing gpt-3.5-turbo is fairly stable on extractive and multiple-choice QA but more variable on free-form answers.
-
A Survey on Large Language Models with some Insights on their Capabilities and Limitations
A broad survey of LLM methods and applications, plus an empirical section on how code-rich pretraining may influence chain-of-thought reasoning, the details of which are not visible in the supplied text.
-
Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience
A survey and taxonomy that organizes AI agentic reasoning into four neuroscience-inspired categories without introducing new empirical results.
-
DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models
A survey of DeepSeek's V3 and R1 models covering MLA, MoE, MTP, GRPO, and training engineering, with no new experimental results.
Discussion (0). Continue with ORCID to comment.