Papers by Lili Jiang

9 papers
LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) are increasingly lengthy and require longer prompts . this paper presents a coarse-to-fine prompt compression method to reduce cost and increase performance.
Approach: They propose a coarse-to-fine prompt compression method that maintains semantic integrity under high compression ratios and a token-level iterative compression algorithm to better model the interdependence between compressed contents.
Outcome: The proposed method yields state-of-the-art performance and allows for up to 20x compression with little performance loss over four datasets from different scenarios.
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.
LeanK: Learnable K Cache Channel Pruning for Efficient Decoding (2025.emnlp-main)

Copied to clipboard

Challenge: Existing efforts to optimize the key-value (KV) cache include: (1) Eviction, which discards cache of less important tokens; (2) Selection, which retains the full KV cache but selectively reads relevant entries.
Approach: They propose a learning-based method that prunes unimportant key (K) cache channels by leveraging static channel sparsity.
Outcome: Experiments show that LeanK reduces GPU memory and accelerates decoding without sacrificing accuracy.
Multimodal Review Generation with Privacy and Fairness Awareness (2020.coling-main)

Copied to clipboard

Challenge: Existing frameworks for generating personalized reviews take privacy and fairness into account . users generate digital footprints when "traveling" on the internet .
Approach: They propose a neural-based framework that generates personalized reviews with privacy and fairness in mind.
Outcome: The proposed framework generates plausibly long reviews while controlling the amount of exploited user data and using the least sentiment biased embeddings.
Accelerating Prefilling via Decoding-time Contribution Sparsity (2026.findings-acl)

Copied to clipboard

Challenge: Existing acceleration methods exploit attention score sparsity by estimating blocks with high attention scores and applying dynamic sparse attention.
Approach: They propose a method which replaces dense attention with Triangle attention in a subset of layers to reduce the time needed to decode.
Outcome: Experiments show that TriangleMix achieves near-lossless performance on long-context and long-constrast reasoning benchmarks while significantly improving efficiency.
Position Engineering: Boosting Large Language Models through Positional Information Manipulation (2024.emnlp-main)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) have demonstrated significant strides towards achieving artificial general intelligence.
Approach: They propose a technique termed position engineering which alters the positional information in the prompt without modifying the text itself.
Outcome: The proposed technique significantly improves on the baseline in retrieval-augmented generation and in-context learning scenarios.
LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression (2024.findings-acl)

Copied to clipboard

Challenge: Existing approaches to compress prompts only leverage unidirectional context, causing suboptimal results.
Approach: They propose a task-agnostic prompt compression method that takes tokens from context . they use a Transformer encoder to capture all essential information needed for prompt compression .
Outcome: The proposed method is 3x-6x faster than existing prompt compression methods and faster than baselines.
RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization (2026.acl-long)

Copied to clipboard

Challenge: Reinforcement Learning with Verifiable Reward (RLVR) has significantly advanced the complex reasoning abilities of Large Language Models (LLMs).
Approach: They propose a hybrid-policy optimization approach that synergizes internal exploitation with external data to achieve stronger reasoning capabilities.
Outcome: The proposed approach achieves state-of-the-art performance on six math reasoning benchmarks and superior performance on out-of distribution reasoning tasks.
LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression (2024.acl-long)

Copied to clipboard

Challenge: Longer prompts introduce irrelevant and redundant information, which can weaken LLMs' performance.
Approach: They propose a prompt compression tool that improves LLMs' perception of key information in input prompts by up to 21.4% with around 4x fewer tokens in GPT-3.5-Turbo.
Outcome: The proposed solution improves performance and reduces costs and latency by up to 21.4% with around 4x fewer tokens in the NaturalQuestions benchmark.

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