Papers with Llama2-7B-Chat

4 papers
Alleviating Hallucinations of Large Language Models through Induced Hallucinations (2025.findings-naacl)

Copied to clipboard

Challenge: Existing studies have shown that large language models generate inaccurate or fabricated information, a phenomenon known as hallucinations.
Approach: They propose a simple strategy to induce-then-contrast decode LLMs to enhance their factuality . they first induce hallucinations from the original model and penalize them .
Outcome: The proposed strategy improves factuality of large language models across task formats, model sizes, and model families.
From Evasion to Concealment: Stealthy Knowledge Unlearning for LLMs (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches to unlearning often treat nonsensical responses or template-based refusals as the unlearning target, making the process even more vulnerable to attacks and jailbreaks.
Approach: They propose a method that uses inverted facts to remove the need for auxiliary models or retaining data while avoiding leakage.
Outcome: Evaluated on the ToFU Knowledge Unlearning dataset using Llama2-7B-Chat and Phi-1.5, MEOW outperforms baselines in forgetting quality while preserving model utility.
Faster In-Context Learning for LLMs via N-Gram Trie Speculative Decoding (2025.emnlp-main)

Copied to clipboard

Challenge: In-Context Learning (ICL) is a key method in prompt engineering, but its long retrieved contexts and limited token throughput will slow reasoning speeds.
Approach: They propose a method that leverages the overlap between context and model output to generate drafts from the context.
Outcome: The proposed method achieves the highest mean speedup on Vicuna-7B, Llama2-7B-Chat, and Llma3-8B-Instruct tasks.
Rethinking Prompt-based Debiasing in Large Language Model (2025.findings-acl)

Copied to clipboard

Challenge: Existing prompt-based methods for debiasing are often superficial and lack a thorough understanding of complex bias concepts.
Approach: They analyze a BBQ and stereoSet benchmarks to examine the assumption that large language models understand biases.
Outcome: The proposed model misclassified 90% of unbiased content as biased despite high accuracy on BBQ dataset . the proposed model may have been flawed in previous attempts to debiase .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations