TaNOS improves cross-domain numerical reasoning over tables by combining header anonymization, operation sketches, and self-supervised pretraining, achieving 80.13% accuracy on FinQA with 10% of training data.
”Evaluating the logical reasoning ability of chatgpt and gpt-4.” arXiv preprint arXiv:2304.03439 (2023)
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
verdicts
UNVERDICTED 6representative citing papers
Introduces NoisyToolBench benchmark and Ask-when-Needed framework to improve LLM tool-use performance when user instructions are unclear or incomplete.
LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.
Novelty estimation via LLM prompts enables pruning in Tree-of-Thought search, reducing overall token usage on language planning benchmarks.
An SCM-GRPO framework grounds multi-hop reasoning in structural dependency graphs and optimizes chain length via rule-based RL, outperforming baselines on HoVer and EX-FEVER.
A goal-oriented chatbot uses family photos to generate W-questions and open prompts for elderly reminiscence, analyzes topics to suggest follow-up photos, and supplies caregivers with conversation insights via a web portal.
citing papers explorer
-
Generalizing Numerical Reasoning in Table Data through Operation Sketches and Self-Supervised Learning
TaNOS improves cross-domain numerical reasoning over tables by combining header anonymization, operation sketches, and self-supervised pretraining, achieving 80.13% accuracy on FinQA with 10% of training data.
-
Learning to Ask: When LLM Agents Meet Unclear Instruction
Introduces NoisyToolBench benchmark and Ask-when-Needed framework to improve LLM tool-use performance when user instructions are unclear or incomplete.
-
LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.
-
Novelty-based Tree-of-Thought Search for LLM Reasoning and Planning
Novelty estimation via LLM prompts enables pruning in Tree-of-Thought search, reducing overall token usage on language planning benchmarks.
-
Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization
An SCM-GRPO framework grounds multi-hop reasoning in structural dependency graphs and optimizes chain length via rule-based RL, outperforming baselines on HoVer and EX-FEVER.
-
A Goal-Oriented Chatbot for Engaging the Elderly Through Family Photo Conversations
A goal-oriented chatbot uses family photos to generate W-questions and open prompts for elderly reminiscence, analyzes topics to suggest follow-up photos, and supplies caregivers with conversation insights via a web portal.