Papers by Shijie Li

21 papers
R2A-TLS: Reflective Retrieval-Augmented Timeline Summarization with Causal-Semantic Integration (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods struggle to capture coherent event narratives due to fragmented descriptions . Existing approaches accumulate noise through iterative retrieval strategies that lack relevance evaluation.
Approach: They propose a reflective retrieval-augmented timeline summarization with Causal-Semantic Intergration approach for open-domain timeline summarizing .
Outcome: The proposed approach outperforms the best prior published approaches.
MARS2: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to reinforcement learning are decoupled from structured search due to limited trajectory diversity.
Approach: They propose a unified RL framework that integrates multiple agents within a shared tree-structured search environment.
Outcome: Experiments show that MARS2 improves performance across diverse model combinations and training settings.
RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement (2025.naacl-long)

Copied to clipboard

Challenge: Existing large language models (LLMs) show exceptional problem-solving capabilities but struggle with complex reasoning tasks.
Approach: They propose a novel RAG approach that integrates retrieved information to guide tree-based reasoning process based on LLMs.
Outcome: The proposed approach outperforms existing methods in large language models . iteratively plans intermediate sub-queries and answers based on the LLM itself .
Joint Semantic and Strategy Matching for Persuasive Dialogue (2023.findings-emnlp)

Copied to clipboard

Challenge: Persuasive dialogue models rely on utterance semantic matching and a key aspect has been ignored . compared with utterrance semantics, conversation strategies are high-level concepts, which can be informative and provide complementary information to achieve effective persuation.
Approach: They propose to model conversation semantics and strategies to match them using a BERT-like module and an auto-regressive predictor.
Outcome: The proposed model improves state-of-the-art by 5% on a small and 37% on 'large' datasets.
Rectified Sparse Attention for Efficient Long-Sequence Generation (2026.findings-acl)

Copied to clipboard

Challenge: Recent sparse decoding methods improve efficiency but suffer from KV cache misalignment, resulting in performance degradation.
Approach: They propose a method that combines block-sparse attention with periodic dense rectification to bound error accumulation and preserve alignment with the pretraining distribution.
Outcome: Experiments on math reasoning, language modeling, and retrieval tasks show that ReSA achieves near-lossless generation quality with significantly improved efficiency.
Musical Score Understanding Benchmark: Evaluating Large Language Models’ Comprehension of Complete Musical Scores (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for musical score understanding are narrow in scope, focusing on isolated fragments, short excerpts, or multiple-choice formulations, rather than supporting holistic reasoning over entire scores.
Approach: They propose a benchmark for score-level musical understanding across textual and visual modalities.
Outcome: The musical score understanding benchmark contains 1,800 question-answer pairs from works by Bach, Beethoven, Chopin, Debussy, and others.
MMDEND: Dendrite-Inspired Multi-Branch Multi-Compartment Parallel Spiking Neuron for Sequence Modeling (2025.acl-long)

Copied to clipboard

Challenge: Vanilla spiking neurons are simplified from complex biological neurons with dendrites, soma, and synapses into single somatic compartments.
Approach: They propose a multi-branch, multi-compartment parallel spiking dendritic neuron with a proportion-adjustable multi-branched structure that enables long-term temporal dependencies.
Outcome: The proposed model achieves better long-sequence modeling capability with fewer parameters and lower energy consumption.
Improving Personalized Explanation Generation through Visualization (2022.acl-long)

Copied to clipboard

Challenge: Existing explainable recommendation models generate repetitive sentences for different items or empty sentences with insufficient details.
Approach: They propose a visual-enhanced approach to generate rating scores and text explanations using visualization generation and text–image matching discrimination.
Outcome: The proposed approach improves both the text quality and the diversity and explainability of the generated explanations.
ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning (2026.acl-long)

Copied to clipboard

Challenge: Existing reasoning-augmented systems that handle complex queries are lacking . we present a framework that enhances LLM-based recommendation assistants .
Approach: They propose a reinforcement fine-tuning framework that enhances LLM-based recommendation . they use a dual-graph Enhanced Reward Shaping framework to integrate recommendation metrics .
Outcome: The proposed framework outperforms state-of-the-art recommendations and preserves core abilities.
HiMATE: A Hierarchical Multi-Agent Framework for Machine Translation Evaluation (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing LLM-based evaluation methods fail to accurately identify error spans and assess their severity.
Approach: They propose a Hierarchical Multi-Agent Framework for Machine Translation Evaluation based on the MQM error typology and a hierarchical multi-agent system enabling granular evaluation of subtype errors.
Outcome: The proposed framework outperforms baselines in error span detection and severity assessment.
Unveiling Inherent Visual Grounding in Multimodal LLMs for Text-Rich Images (2026.findings-acl)

Copied to clipboard

Challenge: Existing multimodal large language model (MLLM) approaches struggle to align query tokens with visual–text patches, heavily relying on lengthy OCR inputs.
Approach: They propose an OCR-free approach that leverages the MLLM's inherent multi-head attention for multi-patch grounding.
Outcome: Empirical results show that the proposed approach outperforms existing approaches on challenging document grounding benchmarks.
Simple-VGC: Enhancing Visual Grounding in Multimodal Reasoning via Adaptive Tool Composition (2026.acl-long)

Copied to clipboard

Challenge: Existing multimodal large language models suffer from systematic failures in basic visual understanding.
Approach: They propose a tool-augmented reasoning framework with three targeted compensation strategies to address these problems.
Outcome: The proposed framework improves visual grounding by re-injecting the original image to mitigate visual forgetting, the authors show . the proposed framework also improves the accuracy of the visual inputs, the researchers show - and the results are promising .
WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for self-improvement of large language models with verifiable rewards (RLVR) can drift over iterations, while corpus-grounded approaches rely on curated data environments.
Approach: They propose a Web-grounded Iterative Self-play Tree framework for domain-targeted reasoning improvement that learns directly from the open-web without requiring any pre-arranged domain corpus.
Outcome: The proposed framework outperforms both purely endogenous self-evolution and corpus-grounded self-play baselines and is domain-steerable.
Emerging Cross-lingual Structure in Pretrained Language Models (2020.acl-main)

Copied to clipboard

Challenge: Recent work has shown that multilingual pretraining works, but is unable to measure these effects.
Approach: They propose to use multilingual masked language modeling to train a model on concatenated text from multiple languages to find universal latent symmetries in embedding spaces.
Outcome: The proposed models can be trained on concatenated text from multiple languages without shared vocabulary or domain similarity.
QPruner: Probabilistic Decision Quantization for Structured Pruning in Large Language Models (2025.findings-naacl)

Copied to clipboard

Challenge: Structured pruning can reduce model size but results in significant accuracy degradation . quantization and pruning increase the difficulty of fine-tuning, requiring a more refined quantization scheme.
Approach: They propose a structured pruning framework followed by a layer-wise mixed-precision quantization scheme to reduce model memory consumption during fine-tuning and inference.
Outcome: Experiments on benchmark datasets show that QPruner outperforms existing methods in memory savings while maintaining or improving model performance.
SAFETY-J: Evaluating Safety with Critique (2024.findings-emnlp)

Copied to clipboard

Challenge: Current methods focus on binary safety classifications and lack detailed critique, limiting their utility for model improvement and user trust.
Approach: They propose a bilingual generative safety evaluator for English and Chinese with critique-based judgment that utilizes a robust training dataset and augmented query-response pairs to assess safety across various scenarios comprehensively.
Outcome: The proposed model improves safety evaluations by assessing the quality of critiques with minimal human intervention.
ToW: Thoughts of Words Improve Reasoning in Large Language Models (2025.naacl-long)

Copied to clipboard

Challenge: Unlike other data augmentation methods, thoughts of words (TOW) views next-word prediction as a core reasoning task and injects fine-grained thoughts into pre-training texts.
Approach: They propose a training-time data-augmentation method called thoughts of words (TOW) that injects fine-grained thoughts directly into a next-word prediction task and teaches the model to understand how the observed next word is related to previous contexts.
Outcome: The proposed method reduces model hallucination by 10% and improves reasoning performance by 7% to 9% on average.
AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists (2025.emnlp-main)

Copied to clipboard

Challenge: AutoSDT-5K is the only automatically collected and the largest open dataset for data-driven scientific discovery.
Approach: They propose an automatic pipeline that collects high-quality coding tasks in real-world data-driven discovery workflows.
Outcome: The proposed pipeline synthesizes accurate tasks and tasks from a dataset of 5,404 tasks covering four scientific disciplines and 756 Python packages.
QA‐LIGN: Aligning LLMs through Constitutionally Decomposed QA (2025.findings-emnlp)

Copied to clipboard

Challenge: QA-LIGN decomposes monolithic rewards into interpretable principle-specific evaluations . scalar rewards obscure which objectives drive the training signal .
Approach: a new method decomposes monolithic rewards into interpretable principle-specific evaluations . QA-LIGN reduces attack success rates by up to 68.7% while maintaining a 0.67% false refusal rate .
Outcome: QA-LIGN reduces attack success rates by up to 68.7% while maintaining a 0.67% false refusal rate . the results outperform DPO and GRPO with state-of-the-art reward models given equivalent training .
AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks focus on single agentic capability, failing to capture long-horizon real-world scenarios.
Approach: They propose a benchmark that evaluates 6 agentic capabilities across 32 real-world scenarios.
Outcome: Experiments show that closed-source models outperform open-source model (48.4% vs 32.1%) integrating models with advanced scaffolds to form autonomous agents is a paradigm shift.
RankAdaptor: Hierarchical Rank Allocation for Efficient Fine-Tuning Pruned LLMs via Performance Model (2025.findings-naacl)

Copied to clipboard

Challenge: Current compression techniques entail structural pruning and a recovery phase that leverages the Low-Rank Adaptation algorithm.
Approach: They propose a hierarchical rank allocation method that enables efficient fine-tuning of pruned LLMs according to layerwise specific recovery requirements.
Outcome: The proposed algorithm outperforms state-of-the-art methods across pruning settings and LLM architectures with improvements ranging from 0.7% to 5.5%.

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