Elamur Research⌕
☰
home / authors / Jingang Wang

Jingang Wang

Jingang Wang has 7 papers in our library, in 2022–2026, most of them on Language models & pretraining, Dialogue systems, Reasoning; often with Fei Sun, Xin Chen, Xueqi Cheng.

7 papers in our library · 2022–2026

OpenAlex · h-index 1 · 20 works · 1 citations OpenAlex, 2026-10-14

📄 7 works in our library · 🔗 Cited 124 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #4391

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🏢MeituanBeijing · China2026 · 15 paperscurrent🎓University of Chinese Academy of SciencesBeijing · China2026 · 2 paperscurrent🎓Fudan UniversityShanghai · China2026 · 1 papercurrent🔬Institute of Computing TechnologyBeijing · China2026 · 1 papercurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 7 worksComputer Science · 7 worksArtificial Intelligence · 7 worksLanguage and Linguistics · 7 worksComputer Vision and Pattern Recognition · 2 worksInformation Systems · 1 work

🧭 Topics 5Research subjects and languages the work is about.Language models & pretraining · 2 worksReasoning · 2 worksDialogue systems · 2 worksEvaluation & benchmarks · 1 workInformation retrieval & search · 1 work

 Works by year

2020s

20264 papers20252 papers20221 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification (2022 · 362 citations)
    Prompt-tuning turns text classification into a masked language modeling task. A template wraps the input, and a verbalizer maps predicted words at the [MASK] position to class labels. Verbalizers are usually handcrafted with a single class-name word or learned from data. Hand-built ones cover too few words and carry…
  2. Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs (2025 · 12 citations)
    LLM error detectors often treat agreement across sampled answers as a sign of correctness. This paper identifies a blind spot in that assumption: self-consistent errors , where a model gives the same wrong answer, up to semantic equivalence, in its greedy output and in all stochastic samples. The authors define these…
  3. Sibyl: Empowering Empathetic Dialogue Generation in Large Language Models via Sensible and Visionary Commonsense Inference (2025 · 9 citations)
    LLM-based chatbots often fall short on empathy and emotional support in multi-turn conversations, even when they are given commonsense knowledge.
  4. The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis (2026 · 6 citations)
    Reasoning LLMs often keep generating "thinking" tokens after they already have enough information to answer, which wastes compute and is known as overthinking.
  5. Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text (2026 · 4 citations)
    Training LLM agents for multi-turn tool use is limited by a shortage of realistic trajectories. Most existing synthesis methods start from a fixed API collection, so the data can only be as broad as that collection. The authors invert this approach. They argue that ordinary web text, such as how-to guides and…
  6. BaseCal: Unsupervised Confidence Calibration via Base Model Signals (2026 · 1 citation)
    Post-trained LLMs (PoLLMs), such as instruction-tuned or RLHF-aligned models, tend to be overconfident: they assign high probability even to wrong answers, which limits the usefulness of confidence for detecting hallucinations.
  7. MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks (2026)
    Conversational retrieval decides which evidence a RAG system can use, but its benchmarks have two kinds of flaws.

All works

8 works of theirs in our library, the most cited first; 7 with a page here, the others link their original until we summarise them.

  1. Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text ClassificationAnnual Meeting of the Association for Computational Linguistics (ACL)Shengding Hu, Ning Ding, Huadong Wang, et al.2022 · 362 citations
  2. Too Consistent to Detect: A Study of Self-Consistent Errors in LLMsConference on Empirical Methods in Natural Language Processing (EMNLP)Hexiang Tan, Fei Sun, Sha Liu, et al.2025 · 12 citations
  3. Sibyl: Empowering Empathetic Dialogue Generation in Large Language Models via Sensible and Visionary Commonsense InferenceInternational Conference on Computational Linguistics (COLING)Lanrui Wang, Jiangnan Li, Chenxu Yang, et al.2025 · 9 citations
  4. The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics AnalysisAnnual Meeting of the Association for Computational Linguistics (ACL)Zihao Wei, Liang Pang, Jiahao Liu, et al.2026 · 6 citations
  5. Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from TextAnnual Meeting of the Association for Computational Linguistics (ACL)Zhihao Xu, Rumei Li, Jiahuan Li, et al.2026 · 4 citations
  6. BaseCal: Unsupervised Confidence Calibration via Base Model SignalsAnnual Meeting of the Association for Computational Linguistics (ACL)Hexiang Tan, Wanli Yang, Junwei Zhang, et al.2026 · 1 citation
  7. MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval BenchmarksAnnual Meeting of the Association for Computational Linguistics (ACL)Junhao Ruan, Abudukeyumu Abudula, Bei Li, et al.2026
  8. LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetXuemiao Zhang et al.2026

 Co-authors here

12 of 34 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 124 times (of the 149,439 papers whose bibliographies we read); 25 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/jingang-wang/