Papers by Wen Hou

11 papers
From Selection to Refinement: Iterative Optimization for Instruction Data (2026.acl-long)

Copied to clipboard

Challenge: Existing methods to optimize instruction tuning datasets face two main challenges: unreasonable pruning of potentially valuable low-quality data and the persistence of noise or semantic drift during revision.
Approach: They propose an automated iterative framework for instruction data optimization that prunes low-quality data and refines low quality data using feedback-driven iteration.
Outcome: The proposed framework outperforms state-of-the-art methods on seven public benchmark datasets with high data efficiency.
COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences (2021.findings-acl)

Copied to clipboard

Challenge: Recent advances in pretrained language models have shown promising results on commonsense reasoning benchmark datasets.
Approach: They propose a commonsense reasoning benchmark dataset with 4k sentence pairs . they propose 'gamified' model-in-the-loop setup to incentivize challenging samples .
Outcome: The proposed benchmarks show that the proposed model achieves 71% standard accuracy and 51% pairwise accuracy, well below human performance.
Lost in Overlap: Exploring Logit-based Watermark Collision in LLMs (2025.findings-naacl)

Copied to clipboard

Challenge: Existing watermarking methods embed imperceptible identifiers into text to address copyright concerns.
Approach: They propose a new philosophy for watermark attacks that addresses watermark collision . they demonstrate that collision poses a threat to all logit-based watermark algorithms .
Outcome: The proposed method improves watermark collision performance on top of other methods.
SpecCache: Speculative KV Cache Reuse for Efficient RAG Serving (2026.acl-long)

Copied to clipboard

Challenge: Retrieval-Augmented Generation (RAG) improves LLMs but faces high prefill latency during long contexts.
Approach: They propose a method that uses deep-layer hidden-state norms to guide token selection . they propose to use deep-layered hidden-status norms as a proxy to guide the token selection.
Outcome: The proposed SpecCache outperforms state-of-the-art (SOTA) benchmarks.
Spec-o3: A Tool-Augmented Vision-Language Agent for Rare Celestial Object Candidate Vetting via Automated Spectral Inspection (2026.acl-long)

Copied to clipboard

Challenge: Spec-o3 is a tool-augmented vision-language agent that performs astronomer-aligned spectral inspection.
Approach: They propose a tool-augmented vision-language agent that performs astronomer-aligned spectral inspection via interleaved multimodal chain-of-thought reasoning.
Outcome: Spec-o3 outperforms traditional visual inspection methods on rare-object inspection tasks.
On Transferability of Prompt Tuning for Natural Language Processing (2022.naacl-main)

Copied to clipboard

Challenge: Pre-trained language models (PLMs) can achieve comparable performance to full-parameter fine-tuning by tuning a few soft prompts, but require much more training time than fine-timing.
Approach: They empirically investigate the transferability of soft prompts across different downstream tasks and PLMs to determine what decides prompt transferability.
Outcome: The proposed method can achieve comparable performance to full-parameter fine-tuning by tuning a few soft prompts, but requires much more training time than fine-timing.
Finding Skill Neurons in Pre-trained Transformer-based Language Models (2022.emnlp-main)

Copied to clipboard

Challenge: Pre-trained language models have demonstrated superior performance on various natural language processing tasks.
Approach: They find that after prompt tuning, some neurons encode task-specific skills . they also show that skill neurons are most likely generated in pre-training .
Outcome: The neurons are highly predictive of task labels after prompt tuning for specific tasks.
Rethinking Table Pruning in TableQA: From Sequential Revisions to Gold Trajectory-Supervised Parallel Search (2026.acl-long)

Copied to clipboard

Challenge: Existing pruning methods rely on sequential revisions and unreliable critique signals . Existing methods fail to detect the loss of answer-critical data .
Approach: They propose a table pruning framework which transforms table pruning to gold trajectory-supervised parallel search.
Outcome: The proposed framework outperforms the strongest baseline pruning framework by 3.2% on various tabular reasoning tasks.
Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via sequence-level likelihood (2026.acl-long)

Copied to clipboard

Challenge: Group Relative Policy Optimization (GRPO) has significantly advanced the reasoning ability of large language models (LLMs).
Approach: They propose a token-level framework that leverages sequence-level likelihood to link group-level rewards with individual tokens via token- level aggregation and introduces a KL-Divergence mask constraint that targets tokens with positive advantages and decreasing entropy to mitigate abrupt policy updates.
Outcome: Experiments show that TEPO achieves state-of-the-art performance on mathematical reasoning benchmarks and reduces convergence time by 50% compared with GRPO/DAPO.
CharacterGLM: Customizing Social Characters with Large Language Models (2024.emnlp-industry)

Copied to clipboard

Challenge: Character-based dialogue systems (CharacterDial) allow users to customize social characters for social interactions.
Approach: They will collect a large-scale Chinese corpus of characters with diverse categories and behaviors and develop CharacterGLM models to address these challenges.
Outcome: Experiments show that CharacterGLM outperforms most popular open- and closed-source LLMs and performs comparable to GPT-4.
Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis (2026.acl-long)

Copied to clipboard

Challenge: Existing mitigation strategies rely on global gradient geometry to resolve alignment conflicts . however, they overlook Modular Heterogeneity within Transformers, resulting in suboptimal trade-offs . Conflict-Aware Sparse Tuning (CAST) combines head-level diagnosis with sparse fine-tuning .
Approach: They propose a framework that integrates head-level diagnosis with sparse fine-tuning to address this limitation.
Outcome: The proposed framework integrates head-level diagnosis with sparse fine-tuning to reduce alignment conflicts in LLMs.

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