Papers with self-generation
Rethinking Prompt Optimizers: From Prompt Merits to Optimization (2026.eacl-long)
Copied to clipboard
Zixiao Zhu, Hanzhang Zhou, Zijian Feng, Tianjiao Li, Chua Jia Jim Deryl, Lee Onn Mak, Gee Wah Ng, Kezhi Mao
| Challenge: | Existing methods to optimize prompts rely on LLMs' self-generation ability but lack interpretability due to implicit optimization. |
| Approach: | They propose a model-agnostic prompt quality merits and a merit-guided, locally deployable prompt optimizer trained on a lightweight LLM to improve prompt quality. |
| Outcome: | The proposed model avoids online optimization, reduces privacy concerns, and generalizes effectively to both large-scale and lightweight inference models. |
DoG-Instruct: Towards Premium Instruction-Tuning Data via Text-Grounded Instruction Wrapping (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods to collect high-quality instruction-response pairs suffer from unaffordable labor costs or severe hallucinations in the self-generation of LLMs. |
| Approach: | They propose a method that trains LLMs to generate instruction-response pairs based on human-written documents rather than relying solely on self-generation without context. |
| Outcome: | The proposed method outperforms existing typical methods on multiple benchmarks and shows that it is 100% scalable. |
Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution (2025.findings-acl)
Copied to clipboard
Kun Li, Tianhua Zhang, Yunxiang Li, Hongyin Luo, Abdalla Mohamed Salama Sayed Moustafa, Xixin Wu, James R. Glass, Helen M. Meng
| Challenge: | Existing methods to improve context faithfulness in large language models are either inadequate or overlook the potential for self-improvement. |
| Approach: | They propose a framework that enhances context faithfulness through fine-grained sentence-level optimization. |
| Outcome: | Experiments on ASQA and ConFiQA datasets show that GenDiE surpasses baselines in faithfulness and correctness and exhibits robust performance for domain adaptation. |
ReActR: Reasoning through Error-Activated Reflection for LLM Post-Training (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for improving the mathematical abilities of Large Language Models (LLMs) focus disproportionately on scaling correct training samples, overlooking the rich learning signals contained in erroneous reasoning trajectories. |
| Approach: | They propose a framework that enhances reasoning by learning reflective behaviors from erroneous trajectories by using data construction and training. |
| Outcome: | Extensive experiments on three LLMs show that ReActR improves reasoning performance on Llama-3-8B. |