Papers by Zhiheng Liu

25 papers
Soundwave: Less is More for Speech-Text Alignment in LLMs (2025.acl-long)

Copied to clipboard

Challenge: Existing end-to-end speech large language models rely on large-scale annotated data for training, while data-efficient training has not been discussed in depth.
Approach: They propose a training strategy and a novel architecture to address representation space gap and sequence length inconsistency in speech and text.
Outcome: The proposed model outperforms other advanced speech LLMs in speech translation and AIR-Bench speech tasks with only a fraction of the training data.
AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks evaluate agents in simplified, idealized settings, relying on pre-packaged tool interfaces, overlooking critical steps, and assume inputs are clean and fully specified.
Approach: They propose a framework that evaluates language agents in simplified, idealized settings . they show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .
Outcome: Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .
LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin (2024.acl-long)

Copied to clipboard

Challenge: Experimental results show that, as the instruction data increases, LoRAMoE can significantly improve the ability to process downstream tasks, while maintaining the world knowledge stored in the LLM.
Approach: They propose a framework that introduces several low-rank adapters and integrates them by using a router network to freeze the backbone model and force a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks.
Outcome: The proposed framework freezes the backbone model and forces a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks, to alleviate world knowledge forgetting.
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing literature on mechanistic interpretation (MI) treats it as an observational science, leaving practical applications underexplored.
Approach: They propose a survey structured around the pipeline to identify and improve MI models.
Outcome: The proposed framework enables tangible improvements in Alignment, Capability, and Efficiency.
Hybrid Hierarchical Retrieval for Open-Domain Question Answering (2023.findings-acl)

Copied to clipboard

Challenge: Recent work shows that dense hierarchical retrieval (DHR) can outperform dense passage retrieval.
Approach: They propose a framework that applies sparse, dense and a combination of them to document and passage retrieval.
Outcome: The proposed framework can outperform dense hierarchical retrieval (DHR) and sparse retrievers (BM25) on open-domain question answering (ODQA) datasets with an average improvement of 4.69% on recall@100 over DHR.
AgentV-RL: Scaling Reward Modeling with Agentic Verifier (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to improve LLM reasoning are limited in complex domains and lack external grounding makes verifiers unreliable on computation-intensive tasks.
Approach: They propose a framework that transforms reward modeling into a multi-turn, tool-augmented deliberative process.
Outcome: The proposed framework surpasses state-of-the-art ORMs by 25.2% under parallel and sequential TTS.
Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing prompting methods have been used to enhance multistep reasoning capabilities of large language models, but they have overlooked the potential of formulating higher-quality problems.
Approach: They propose a method that starts from the problem side and refines problems to be more comprehensible and solvable for models.
Outcome: The proposed method achieves notable and consistent effectiveness on five reasoning benchmarks across different models.
Multi-Programming Language Sandbox for LLMs (2025.acl-demo)

Copied to clipboard

Challenge: MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs).
Approach: They propose a multi-programming language sandbox that provides unified feedback from compilers and analysis tools for Large Language Models.
Outcome: The proposed multi-language sandbox can provide comprehensive feedback from compilers and analysis tools for large language models (LLMs).
Hetero-Designer: Automated Design of Multi-Agent Systems with Heterogeneous LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to design LLM-based Multi-agent systems are constrained by homogeneous LLMs.
Approach: They propose an automated design of heterogeneous-LLMs-based MAS with a binary-star transformer and an autoregressive graph generation pipeline.
Outcome: The proposed pipeline is high-performing on various benchmarks and extensible to unseen LLMs and roles.
VENUS: A VLLM-driven Video Content Discovery System for Real Application Scenarios (2025.emnlp-industry)

Copied to clipboard

Challenge: Video Content Discovery (VCD) is to identify specific videos defined by a pre-specified text policy.
Approach: They propose a Vision-Language Large Model-driven video content discovery system called VENUS to solve these problems.
Outcome: The proposed system generates high-quality, VCD-specific data for model training and extends it to support it better.
LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing evaluation of Large Language Models on static benchmarks is vulnerable to data contamination and leaderboard overfitting.
Approach: LLMEval-Fair framework provides a framework for dynamic evaluation of Large Language Models . evaluators use a proprietary bank of 220k graduate-level questions to analyze model data .
Outcome: LLMEval-Fair provides robust and credible evaluation framework for Large Language Models . it provides a strong empirical validation for the dynamic evaluation paradigm .
A Systematic Assessment of Language Models with Linguistic Minimal Pairs in Chinese (2026.tacl-1)

Copied to clipboard

Challenge: Using sub-linear length normalized log-probabilities (SLLN-LP), we find unequal lengths of sentences in minimal pairs difficult for LMs even up to 32B parameters.
Approach: They propose to use ZhoBLiMP as a linguistic minimal pair benchmark for Chinese language models to mitigate biases.
Outcome: The proposed metric mitigates biases in Chinese language models with over 100 paradigms . Anaphor, Quantifiers, and Ellipsis are difficult for LMs even up to 32B parameters .
RobustQA: Benchmarking the Robustness of Domain Adaptation for Open-Domain Question Answering (2023.findings-acl)

Copied to clipboard

Challenge: Existing ODQA datasets consist mainly of Wikipedia corpus, and are insufficient to study models’ generalizability across diverse domains.
Approach: They propose a benchmark to evaluate ODQA's domain robustness using Wikipedia corpus . they annotate QA pairs in retrieval datasets with rigorous quality control .
Outcome: The proposed benchmark improves model performance on annotated QA pairs in retrieval datasets with rigorous quality control.
Characterizing the Impacts of Instances on Robustness (2023.findings-acl)

Copied to clipboard

Challenge: Existing defense approaches focus on developing new model structures or training algorithms, but they do little to tap the potential of training instances.
Approach: They propose a method that can distinguish between robust and non-robust instances according to the model’s sensitivity to perturbations on individual instances during training.
Outcome: The proposed method can distinguish between robust and non-robust instances according to the model’s sensitivity to perturbations on individual instances during training.
Improving Cross-task Generalization of Unified Table-to-text Models with Compositional Task Configurations (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for multitask learning typically use a dataset name as input prefix, which limits the effectiveness of multitask training.
Approach: They propose compositional task configurations, a set of prompts prepended to the encoder to improve cross-task generalization of unified models.
Outcome: The proposed model outperforms the UnifiedSKG baseline by noticeable margins in both in-domain and zero-shot settings.
Toward Optimal LLM Alignments Using Two-Player Games (2025.findings-emnlp)

Copied to clipboard

Challenge: Alignment of large language models (LLM) is a process that ensures the model’s responses to user prompts align with human intentions and social values.
Approach: They propose an alignment method based on a two-agent game consisting of an adversarial agent and a defensive agent.
Outcome: The proposed method improves on a two-agent game with an adversarial agent and a defensive agent.
MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Challenge: Existing work on long document visual question answering is based on Retrieval-Augmented Generation (RAG) where textual or visual content is encoded into embeddings and relevance is determined by similarity scores with respect to the original query.
Approach: They propose a framework that employs an agentic, vision-aware workflow to address long document visual question answering through iterative information discovery and synthesis.
Outcome: The proposed framework outperforms existing RL systems by 10.4% on the MMLongbench-Doc benchmark and demonstrates superior training performance over GRPO.
LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation (2025.findings-emnlp)

Copied to clipboard

Challenge: Current medical benchmarks have limitations in question design, data sources and evaluation methods.
Approach: They propose a new benchmark covering five core medical areas . it includes 2,996 questions created from real-world electronic health records .
Outcome: The proposed model covers five core medical areas and includes 2,996 questions created from real-world electronic health records and expert-designed clinical scenarios.
Language Agnostic Multilingual Information Retrieval with Contrastive Learning (2023.findings-acl)

Copied to clipboard

Challenge: Annotated training data is costly to obtain in many languages .
Approach: They propose a semantic contrastive loss to align parallel sentences that share the same semantics in different languages and a language contrastive gain to leverage parallel sentence pairs to remove language-specific information from non-parallel corpora.
Outcome: The proposed model improves retrieval performance while requiring less computational effort.
Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models (2024.findings-naacl)

Copied to clipboard

Challenge: Existing methods that rely on limited demos and out-of-demonstration (OOD) queries fail when faced with out- of-demotion queries.
Approach: They propose a query-aware prompting method that elicits the inherent generalizability of large language models by query-based demo generation.
Outcome: The proposed method outperforms state-of-the-art methods in the OOD setting and two public math benchmarks.
ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have redefined the role of AI in software engineering . current benchmarks focus on localized code generation, but neglect dynamic, full-process requirements of real-world engineering.
Approach: They propose a benchmark to evaluate agentic backend coding within a realistic, executable workflow.
Outcome: The ABC-Bench benchmark evaluates agentic backend coding within a realistic, executable workflow.
StepCoder: Improving Code Generation with Reinforcement Learning from Compiler Feedback (2024.acl-long)

Copied to clipboard

Challenge: Existing work integrates reinforcement learning with compiler feedback to enhance code generation quality but the long code generated by LLMs makes RL exploration ineffective.
Approach: They propose a framework that integrates reinforcement learning and compiler feedback to enhance code generation quality.
Outcome: The proposed framework outperforms state-of-the-art approaches in corresponding benchmarks and integrates reinforcement learning with compiler feedback to improve code generation quality.
Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks (2023.findings-emnlp)

Copied to clipboard

Challenge: Pretrained sequence-to-sequence (seq2sequ) models have been widely used to solve extractive tasks, where parts of the input are extracted to form the desired output.
Approach: They propose a simple fix to tokenization inconsistency that damages extractive nature of generative models by causing performance drop and hallucination.
Outcome: The proposed model performs better in both in-domain and out-of-domain datasets with a notable average of +1.7 F1 gain when a BART model is trained on SQuAD and evaluated on 8 QA datasets.
Are LLMs Rational Investors? A Study on the Financial Bias in LLMs (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies on biases within specific domains, such as finance, remain limited.
Approach: They propose a framework to detect, detect, analyze and mitigate financial biases in large language models.
Outcome: The proposed framework reduces bias by 68% for the most biased model, according to key metrics.
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)

Copied to clipboard

Challenge: Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction.
Approach: They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack.
Outcome: The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses.

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