Papers by Fan Feng

34 papers
S2S-Arena: Evaluating Paralinguistic Instruction Following in Speech-to-Speech Models (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks rely heavily on text-based evaluation and largely ignore paralinguistic cues such as prosody, emotion, and speaker traits.
Approach: They propose a speech-native benchmark for evaluating instruction-following S2S models with explicit assessment of both semantic understanding and paralinguistic expression.
Outcome: The proposed system enables more natural, robust, and human-aligned speech agents.
LOT: A Story-Centric Benchmark for Evaluating Chinese Long Text Understanding and Generation (2022.tacl-1)

Copied to clipboard

Challenge: Existing benchmarks for natural language processing focus on understanding or generating short texts . lack of standardized benchmarks makes it difficult to assess and compare models .
Approach: They propose a story-centric benchmark for Chinese long text modeling that aggregates two understanding tasks and two generation tasks.
Outcome: The proposed model outperforms similar-sized models on understanding and generation tasks.
Harmful Factuality: LLMs Correcting What They Shouldn’t (2026.findings-eacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are trained for factual accuracy, but can conflict with the critical demand for source fidelity.
Approach: They propose a reproducible framework to elicit and measure HFH using controlled entity-level perturbations and strategic entity selection.
Outcome: The proposed framework reduces HFH rates by 50% across summarization, rephrasing, and QA tasks.
Towards Human-aligned Evaluation for Linear Programming Word Problems (2024.lrec-main)

Copied to clipboard

Challenge: Existing evaluation methodologies for MWPs diverge from human judgment and face challenges in recognizing mathematically equivalent answers.
Approach: They propose an evaluation metric rooted in graph edit distance that features benefits such as permutation invariance and more accurate program equivalence identification.
Outcome: The proposed evaluation metric features benefits such as permutation invariance and more accurate program equivalence identification.
Reinforced Product Metadata Selection for Helpfulness Assessment of Customer Reviews (D19-1)

Copied to clipboard

Challenge: a helpful review is largely concerned with the metadata of its target product . a selector learns from both the key-value product metadata and one of its reviews to take an action .
Approach: They propose a framework that uses product metadata to assess helpfulness of free-text reviews . they use two real-world datasets from amazon.com and Yelp.com to test the framework .
Outcome: The proposed framework can achieve state-of-the-art performance with substantial improvements . it uses two real-world datasets from Amazon.com and Yelp.com .
Alleviating Hallucinations from Knowledge Misalignment in Large Language Models via Selective Abstention Learning (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) suffer from severe hallucination issues due to the knowledge misalignment between the pre-training stage and the supervised fine-tuning stage.
Approach: They propose a training objective with an abstention mechanism that selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token.
Outcome: The proposed model selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token.
Conversational Recommender System and Large Language Model Are Made for Each Other in E-commerce Pre-sales Dialogue (2023.findings-emnlp)

Copied to clipboard

Challenge: E-commerce pre-sales dialogues elicit user needs and preferences for items . large language models lack domain-specific knowledge for accurate recommendations .
Approach: They propose two collaboration strategies to integrate CRS and large language models in pre-sales dialogues.
Outcome: The proposed methods can be very effective in some cases, the authors say .
Multi-grained Attention Network for Aspect-Level Sentiment Classification (D18-1)

Copied to clipboard

Challenge: Existing approaches to aspect sentiment classification use coarse-grained attention mechanisms . a novel approach captures word-level interaction between aspect and context .
Approach: They propose a novel multi-grained attention network model for aspect level sentiment classification . they use a fine-grounded attention mechanism to capture word-level interaction between aspect and context .
Outcome: The proposed model outperforms the state-of-the-art methods on three datasets . it shows that aspect-level interactions can bring extra useful information and improve performance .
SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment (2025.coling-main)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated significant improvements in reasoning abilities, but these improvements are primarily focused on English, leading to inferior performance in non-English scenarios.
Approach: They propose a multilingual reasoning alignment approach that fine-tunes the layers responsible for multilingual comprehension in one stage.
Outcome: The proposed method fine-tunes 6 of the 9 layers responsible for multilingual comprehension, while reducing training time by 4.1-11.9 compared to the two-stage method.
ProMCP: Profiling Token Flows and Latency Costs in Model Context Protocol–Based LLM Agents (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models are increasingly used as agents that interact with external tools and data sources to solve tasks that require fresh knowledge, precise computation, or action in a real environment.
Approach: They propose a framework that decomposes the MCP workflow into a six-stage communication pipeline and enables granular attribution of computational costs.
Outcome: The proposed framework decomposes the MCP workflow into a six-stage communication pipeline, enabling granular attribution of computational costs.
DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to planning involve implicit planning or introduce explicit planners without systematically optimizing the planning stage.
Approach: They propose an end-to-end RL framework that enhances the planning capabilities of deep research agents.
Outcome: Experiments show that DeepPlanner improves planning quality and achieves state-of-the-art results under a lower training budget.
AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (2026.acl-long)

Copied to clipboard

Challenge: Existing knowledge graph construction frameworks require predefined schemas, limiting their scalability and domain coverage.
Approach: They propose a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas.
Outcome: The proposed framework outperforms state-of-the-art models on multi-hop QA tasks and enhances LLM factuality.
PlatoLM: Teaching LLMs in Multi-Round Dialogue via a User Simulator (2024.acl-long)

Copied to clipboard

Challenge: Recent efforts to democratize ChatGPT have focused on leveraging real user and ChatGPP dialogues, but the most direct human needs are often ignored.
Approach: They propose a method to simulate human behavior better by using real human-like questions extracted from real human conversations as a learning goal and a user simulator called ‘Socratic’.
Outcome: The proposed model achieves SoTA performance among LLaMA-based 7B models in MT-Bench.
Empowering Reliable Visual-Centric Instruction Following in MLLMs (2026.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks for evaluating instruction-following capabilities focus on verbal instructions in the textual modality.
Approach: They propose to incorporate vision-dependent constraints into instruction design to enable a more rigorous assessment of how well MLLMs align their outputs with both visual input and textual instructions.
Outcome: The proposed benchmark incorporates vision-dependent constraints into instruction design, enabling a more rigorous and fine-grained assessment of how well MLLMs align their outputs with both visual input and textual instructions.
Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Large vision-language models exhibit an imbalance in multilingual capabilities .
Approach: They propose a training recipe that achieves efficient multilingual enhancement for LVLMs by Precise Language Specific layers fine-tuning.
Outcome: The proposed training recipe achieves efficient multilingual enhancement for LVLMs by fine-tuning language specific layers.
Improving Factual Consistency of News Summarization by Contrastive Preference Optimization (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in news summarization have created problems with “hallucinations” that are factually inconsistent with the source text.
Approach: They propose to disentangle LLMs’ propensities to generate faithful and fake content by adopting a probing-based specific training method to improve their capacity of distinguishing two types of propensity.
Outcome: The proposed method disentangles LLMs’ propensities to generate faithful and fake content and improves their ability to distinguish between two types of propensity.
FlowSearch: Advancing Deep Research with Dynamic Structured Knowledge Flow (2026.acl-long)

Copied to clipboard

Challenge: FlowSearch is a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning.
Approach: They propose a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning.
Outcome: The proposed framework achieves competitive performance on GAIA, HLE, GPQA and TRQA benchmarks and is available to download.
DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration (2025.findings-acl)

Copied to clipboard

Challenge: Long-context understanding is crucial for many NLP applications, but transformers struggle with efficiency due to quadratic complexity of self-attention.
Approach: They propose a dynamic sparse attention mechanism that assigns adaptive masks at the attention-map level, preserving heterogeneous attention patterns.
Outcome: The proposed method achieves high alignment with full-attention models while reducing memory and compute overhead.
MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities.
Approach: They propose a comprehensive benchmark covering 29 languages, built on an English benchmark.
Outcome: The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark.
ACCESS : A Benchmark for Abstract Causal Event Discovery and Reasoning (2025.naacl-long)

Copied to clipboard

Challenge: Existing methods for identifying event causality in NLP are limited in their scale and rely on lexical cues.
Approach: They propose a benchmark for identifying abstract causality from a large-scale dataset.
Outcome: The proposed benchmark can be leveraged for enhancing QA reasoning performance in LLMs.
DP-GTR: Differentially Private Prompt Protection via Group Text Rewriting (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for prompt privacy focus on document-level rewriting, neglecting rich, multi-granular representations of text.
Approach: a framework that leverages local differential privacy and composition theorem via group text rewriting is proposed . the framework is compatible with existing rewrite techniques and is publicly available at anonymous.4open.science for reproducibility.
Outcome: DP-GTR is the first framework to integrate document-level and word-level information while exploiting in-context learning to improve privacy and utility.
Improving Dialogue Discourse Parsing via Reply-to Structures of Addressee Recognition (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to learn dialogue discourse parsing with related tasks require additional annotation, thus limiting their generality.
Approach: They propose a multitasking framework that integrates dialogue discourse parsing with addressee recognition to reflect relation-based structure of dialogue.
Outcome: The proposed framework outperforms baselines on the Molweni and STAC datasets.
DeTriever: Decoder-representation-based Retriever for Improving NL2SQL In-Context Learning (2025.coling-main)

Copied to clipboard

Challenge: In-context Learning (ICL) has proven to be effective in a variety of complex tasks, but the selection of the most beneficial demonstration examples remains an open research problem.
Approach: They propose a demonstration retrieval framework that learns a weighted combination of LLM hidden states where rich semantic information is encoded.
Outcome: Experiments on two popular NL2SQL benchmarks show that the proposed method outperforms state-of-the-art models.
Exploring Reasoning Reward Model for Agents (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for agentic reinforcement learning rely on sparse outcome-based reward for training, leading to suboptimal results.
Approach: They propose an agent-based reward model that produces structured feedback for agentic trajectories, including an explicit reasoning trace and a focused critique.
Outcome: The proposed model produces structured feedback for agentic trajectories including an explicit reasoning trace, a focused critique, and an overall score that evaluates process performance.
Thinking Traps in Long Chain-of-Thought: A Measurable Study and Trap-Aware Adaptive Restart (2026.findings-acl)

Copied to clipboard

Challenge: Experiments show that extended generation does not guarantee correctness . a recurring pattern in Long-CoT failures is a problem for large reasoning models .
Approach: They propose a test-time control framework that truncates the trajectory before the trap segment and adaptively restarts decoding.
Outcome: Experiments show that TAAR improves reasoning performance without fine-tuning model parameters.
Key Mention Pairs Guided Document-Level Relation Extraction (2022.coling-1)

Copied to clipboard

Challenge: Document-level Relation Extraction (DocRE) aims to identify the relations between entities in a given document.
Approach: They propose a document-level relation extraction model with two modules to model mention-level relations.
Outcome: The proposed model outperforms existing state-of-the-art models on two public DocRE datasets and outperformed existing models.
Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have produced significant advances in the field of recommender systems.
Approach: They propose to retrieve up-to-date structure information from the knowledge graph to augment recommendations by leveraging external knowledge sources.
Outcome: Experiments on a large dataset show that the proposed method is effective in enhancing LLM-based recommendations.
Uncovering the Potential of ChatGPT for Discourse Analysis in Dialogue: An Empirical Study (2024.lrec-main)

Copied to clipboard

Challenge: Large language models have shown remarkable capability in many downstream tasks, yet their ability to understand discourse structures of dialogues remains less explored.
Approach: They aim to systematically inspect ChatGPT’s performance in two discourse analysis tasks: topic segmentation and discourse parsing.
Outcome: The proposed model can give more reasonable topic structures than human annotations but only linearly parses the hierarchical rhetorical structures.
HoWToBench: Holistic Evaluation for LLM’s Capability in Human-level Writing using Tree of Writing (2026.acl-long)

Copied to clipboard

Challenge: Evaluating the writing capabilities of large language models remains a significant challenge due to the multidimensional nature of writing skills and the limitations of existing metrics.
Approach: They propose to model the aggregation weights of sub-features in a tree-structured workflow and propose a Chinese writing benchmark that mitigates biases.
Outcome: The proposed tree-of-writing (ToW) measures the writing capabilities of large language models (LLMs) in Chinese and shows that it mitigates biases and achieves a *0.93* Pearson correlation with human judgments.
OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics (2021.acl-long)

Copied to clipboard

Challenge: Existing automatic metrics are observed to correlate poorly with human evaluation.
Approach: They propose to use OpenMEVA to evaluate open-ended story generation metrics.
Outcome: The proposed test suite assesses the capabilities of open-ended story generation metrics on annotated stories and auto-constructed test examples.
Advancing Large Language Model Attribution through Self-Improving (2024.emnlp-main)

Copied to clipboard

Challenge: Teaching large language models to generate text with citations to evidence sources requires high-quality attribution data, which is costly and labor-intensive.
Approach: They propose a framework for iteratively improving the attribution capability of large language models (LLMs) by attributing output to verifiable sources.
Outcome: Experiments on three open-domain question-answering datasets show that START improves in aggregating information across multiple sources.
Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning (2025.emnlp-industry)

Copied to clipboard

Challenge: Existing methods for video temporal grounding suffer from limited temporal awareness and poor generalization.
Approach: They propose a two-stage training framework that integrates supervised fine-tuning with reinforcement learning to improve both the accuracy and robustness of VTG models.
Outcome: The proposed training framework outperforms existing models on multiple benchmarks on open-domain and challenging scenarios.
Not Just Classification: Recognizing Implicit Discourse Relation on Joint Modeling of Classification and Generation (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods of implicit discourse relation recognition (IDRR) focus on three aspects: enhancing discourse units representation, enhancing semantic interaction, and joint learning with other tasks.
Approach: They propose a joint model to recognize the relation label and generate the target sentence containing the meaning of relations simultaneously.
Outcome: The proposed model achieves the best performance against several state-of-the-art systems on Chinese and English datasets.
Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization (2025.acl-long)

Copied to clipboard

Challenge: Existing frameworks for retrieval-augmented large language models (LLMs) are lacking in LFQA faithfulness testing.
Approach: They propose a framework to teach retrieval-augmented large language models to explicitly discriminate between faithful and unfaithful generations.
Outcome: The proposed framework outperforms GPT-4o in LFQA scenarios and outperformed existing benchmarks.

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