Papers by Yifan Zeng

16 papers
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling (2025.findings-emnlp)

Copied to clipboard

Challenge: Best-of-N (BoN) sampling generates multiple responses and selects the best one, achieving improved performance but with a high computational cost.
Approach: They propose a framework that integrates a speculative tree-search strategy into Best-of-N (BoN) Sampling.
Outcome: The proposed framework outperforms Best-of-N (BoN) sampling but has high computational cost . tree-search strategy reduces computational overhead while maintaining high output quality .
ChatEL: Entity Linking with Chatbots (2024.lrec-main)

Copied to clipboard

Challenge: Entity Linking (EL) is a challenging task in natural language processing . existing approaches focus on creating elaborate contextual models that are unwieldy and difficult to train .
Approach: They propose a framework to prompt LLMs to return accurate results for Entity Linking . they use a three-step framework to generate a set of EL models that can be open-source .
Outcome: The proposed framework improves the average F1 performance across 10 datasets by more than 2%.
Aligning Large Language Models with Implicit Preferences from User-Generated Content (2025.acl-long)

Copied to clipboard

Challenge: Existing preference learning methods rely heavily on curated data from humans or advanced LLMs, which is costly and difficult to scale.
Approach: They propose a framework that leverages implicit preferences in unlabeled user-generated content to generate preference data.
Outcome: The proposed framework transforms user-generated content into user queries and generates responses from the policy model.
Retrieval Augmented Fact Verification by Synthesizing Contrastive Arguments (2024.acl-long)

Copied to clipboard

Challenge: Existing methods to verify claim credibility rely on embedded knowledge or unreliable context.
Approach: They propose retrieval augmented fact verification through the synthesis of contrasting arguments (RAFTS) they use an embedding model to identify informative demonstrations and in-context prompts to generate the prediction and explanation.
Outcome: The proposed method outperforms existing methods with smaller LLMs or unreliable contexts.
Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for hallucination detection focus on implicit neural uncertainty or explicit symbolic reasoning, ignoring factual hallucinosities.
Approach: They propose a framework that bridges neural features and symbolic judgments for hallucination detection by leveraging a "meta-judgment" process to map symbolic labels back into the feature space.
Outcome: Extensive experiments on 4 public datasets, across 4 LLMs, against 8 baselines demonstrate the superiority of LaaB.
NUMINA: A Natural Understanding Benchmark for Multi-dimensional Intelligence and Numerical Reasoning Abilities (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing 3D benchmarks lack fine-grained numerical reasoning task annotations, limiting MLLMs’ ability to perform precise spatial measurements and complex numerical reasoning.
Approach: They propose a 3D-based benchmark to enhance indoor perceptual understanding by using multi-scale annotations and question-answer pairs.
Outcome: The proposed benchmark improves indoor perceptual understanding by incorporating multi-scale annotations and question-answer pairs.
Improving Consistency for Text Summarization with Energy Functions (2023.findings-emnlp)

Copied to clipboard

Challenge: Current abstractive summarization models generate inconsistent content due to the inherently noisy dataset and the discrepancy between maximum likelihood estimation based training objectives and consistency measurements.
Approach: They propose a new consistency taxonomy that categorizes inconsistent content into faithfulness, factuality, and self-supportiveness.
Outcome: Experiments on XSUM and CNN/DM datasets show that EnergySum mitigates the trade-off between accuracy and consistency.
ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) have shown excellent mastering of human language but struggle in real-world applications that require mathematical problem-solving.
Approach: They propose a pipeline to train a general Math-Critique model from the LLM itself to provide feedback signals and employ rejective fine-tuning and direct preference optimization over the Llm's own generations for data collection.
Outcome: The proposed pipeline outperforms existing LLMs that could be two times larger.
Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies focus on single-turn scenarios, which might lack the ability to handle multi-turn interactions.
Approach: They propose a conversational agent that interleaves search and reasoning across turns and provides tailored rewards towards evolving user goals.
Outcome: The proposed agent interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through reinforcement learning (RL) training with tailored rewards towards evolving user goals.
Large Language Models Are Poor Clinical Decision-Makers: A Comprehensive Benchmark (2024.emnlp-main)

Copied to clipboard

Challenge: Existing studies focus on evaluating large language models in close-ended QA tasks, but many clinical decisions involve answering open-ended questions without pre-set options.
Approach: They construct a benchmark to better understand large language models in the clinic . they use existing datasets to evaluate LLMs in clinical situations .
Outcome: The proposed model outperforms human experts in multiple medical tasks.
The Ranking Blind Spot: Decision Hijacking in LLM-based Text Ranking (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated strong performance in information retrieval tasks like passage ranking.
Approach: They propose two attacks that aim to force the LLM ranker to prefer a specific passage and rank it at the top.
Outcome: The proposed attacks aim to force the LLM ranker to prefer a specific passage and rank it at the top.
HighMATH: Evaluating Math Reasoning of Large Language Models in Breadth and Depth (2025.findings-emnlp)

Copied to clipboard

Challenge: a gap in math models' accuracy has been widened with the development of large language models (LLMs) . a new study aims to bridge this gap by evaluating a set of high-level math reasoning models .
Approach: They propose to evaluate large language models on existing math benchmarks to bridge this gap . they collect 5,293 problems from Chinese senior high school mathematics exams .
Outcome: The proposed model is based on o1-like models and a high-level model.
Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences (2022.naacl-main)

Copied to clipboard

Challenge: Existing models for long sequences are not efficient due to the quadratic space and time complexity of the self-attention modules.
Approach: They propose to reduce the quadratic complexity to linear (modulo logarithmic factors) by low-dimensional projection and row selection.
Outcome: The proposed methods outperform transformer-based models with smaller time/space footprint on the Long Range Arena benchmark.
Divide, Optimize, Merge: Scalable Fine-Grained Generative Optimization for LLM Agents (2025.findings-emnlp)

Copied to clipboard

Challenge: LLM-based generative optimization has shown remarkable potential in improving agentic systems, but the current approach of prompting with the trajectories on the whole training dataset becomes untenable as datasets grow.
Approach: They propose a scalable framework that divides large optimization tasks into manageable subsets and performs targeted optimizations.
Outcome: The proposed framework outperforms conventional approach by 1.6-8.6% while reducing average prompt token consumption by 56.3%.
Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Recent work has shown that language models (LMs) have strong multi-step (i.e., procedural) reasoning capabilities.
Approach: They propose a mechanistic interpretation of language models for multi-step reasoning tasks by introducing a new probing approach that recovers the reasoning tree from the model’s attention patterns.
Outcome: The proposed model implicitly embeds a reasoning tree resembling the correct reasoning process within it, and detects the information from the model’s attention patterns for most examples.
SimpleDoc: Multi‐Modal Document Understanding with Dual‐Cue Page Retrieval and Iterative Refinement (2025.emnlp-main)

Copied to clipboard

Challenge: Document Visual Question Answering (DocVQA) is a task to answer questions based on documents containing text, tables, and images.
Approach: They propose a lightweight retrieval framework that uses visual language models to embed and retrieve relevant pages as images and generate answers with VLMs that can accept an image as input.
Outcome: The proposed framework outperforms baselines by 3.2% on average on 4 DocVQA datasets with much fewer pages retrieved.

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