Papers by Liyi Chen

4 papers
Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models (2026.acl-long)

Copied to clipboard

Challenge: Existing efficient reasoning methods rely on explicit length penalties for excessive verbosity on simple queries.
Approach: They propose a training-time intervention that selectively suppresses redundant tokens . they find length shift occurs when models generate unnecessary reasoning on trivial inputs - a phenomenon that is often unexplored .
Outcome: The proposed method reduces inference token usage by 78% while increasing accuracy compared to the initial policy and surpasses state-of-the-art efficient reasoning methods.
McQueen: a Benchmark for Multimodal Conversational Query Rewrite (2022.emnlp-main)

Copied to clipboard

Challenge: Recent studies have focused on conversational-related tasks that involve drawing information from more than one modality.
Approach: They propose a task of multimodal conversational query rewrite which performs query . they collect a large-scale visual conversation dataset and benchmark it against other tasks .
Outcome: The proposed task performs on a large-scale visual conversation dataset . it eliminates coreference and ellipsis in the original query without changing its semantic information.
TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection (2025.emnlp-main)

Copied to clipboard

Challenge: Rapid advances in Large Language Models have spurred demand for processing extended context sequences . however, performance degradation due to sequence lengths out-of-distribution and excessively long inference times are limiting LLMs in long-context scenarios.
Approach: They propose a training-free method for efficient and accurate long-context inference . they selectively involves a few critical KV cache tokens in attention calculation .
Outcome: The proposed method speeds up attention computation and accelerates inference time while reducing selection overhead.
CO3: Low-resource Contrastive Co-training for Generative Conversational Query Rewrite (2024.lrec-main)

Copied to clipboard

Challenge: Recent advances in conversational IR systems have seen a resurgent interest in conversation . generative query rewrite generates reconstructed query based on the conversation history .
Approach: They propose to use unlabeled data to make further improvements using contrastive co-training paradigm.
Outcome: The proposed model is robust to noise and language style shift under few-shot and zero-shot scenarios.

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