Papers by Yijiong Yu

3 papers
Mitigate Position Bias in LLMs via Scaling a Single Hidden States Channel (2025.findings-acl)

Copied to clipboard

Challenge: Long-context language models exhibit position bias, also known as "lost in the middle" research shows that even long-contemporary LLMs fail to utilize all context information effectively .
Approach: They propose a method to mitigate position bias by scaling positional hidden states . they propose to use a channel of hidden states to modify positional Hidden states a LCLM's positional bias .
Outcome: The proposed method can improve performance by 15.2% in a "lost in the middle" benchmark.
Long-context Language Models Fail in Basic Retrieval Tasks Without Sufficient Reasoning Steps (2025.findings-emnlp)

Copied to clipboard

Challenge: despite their extensive context window, long-context language models fail in some basic cases . a recent study shows that long-cot methods are not necessary for long-constituency tasks .
Approach: a new study evaluates long-context language models with a large context window . the authors propose a method that can be well addressed with arbitrary reasoning steps .
Outcome: The proposed methods are well addressed with a sufficient number of reasoning steps, guided by specific CoT prompts.
Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for parallelizable reasoning tasks are inefficient, says a new study . generating lengthy reasoning sequences is computationally expensive and time-consuming, says the study authors .
Approach: They propose a method that decodes multiple tokens per forward pass using a tree-like attention mask . their method achieves nearly 100% speedup in decoding while basically maintaining the answer quality .
Outcome: Experimental results show that the method achieves nearly 100% speedup in decoding while maintaining the answer quality.

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