Pith. sign in

REVIEW 7 cited by

Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2408.04638 v2 pith:ITFJSHL5 submitted 2024-07-30 cs.CL cs.CY

Yiqun Zhang , Xiaocui Yang , Xingle Xu , Zeran Gao , Yijie Huang , Shiyi Mu , Shi Feng , Daling Wang
show 3 more authors
Yifei Zhang Kaisong Song Ge Yu
This is my paper
classification cs.CLcs.CY
keywords affectivelanguagemodelssurveyacrosscomputingevaluationgeneration
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Affective Computing (AC) integrates computer science, psychology, and cognitive science to enable machines to recognize, interpret, and simulate human emotions across domains such as social media, finance, healthcare, and education. AC commonly centers on two task families: Affective Understanding (AU) and Affective Generation (AG). While fine-tuned pre-trained language models (PLMs) have achieved solid AU performance, they often generalize poorly across tasks and remain limited for AG, especially in producing diverse, emotionally appropriate responses. The advent of Large Language Models (LLMs) (e.g., ChatGPT and LLaMA) has catalyzed a paradigm shift by offering in-context learning, broader world knowledge, and stronger sequence generation. This survey presents an NLP-oriented overview of AC in the LLM era. We (i) consolidate traditional AC tasks and preliminary LLM-based studies; (ii) review adaptation techniques that improve AU/AG, including Instruction Tuning (full and parameter-efficient methods such as LoRA, P-/Prompt-Tuning), Prompt Engineering (zero/few-shot, chain-of-thought, agent-based prompting), and Reinforcement Learning. For the latter, we summarize RL from human preferences (RLHF), verifiable/programmatic rewards (RLVR), and AI feedback (RLAIF), which provide preference- or rule-grounded optimization signals that can help steer AU/AG toward empathy, safety, and planning, achieving finer-grained or multi-objective control. To assess progress, we compile benchmarks and evaluation practices for both AU and AG. We also discuss open challenges-from ethics, data quality, and safety to robust evaluation and resource efficiency-and outline research directions. We hope this survey clarifies the landscape and offers practical guidance for building affect-aware, reliable, and responsible LLM systems.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Can LLMs Think Like Consumers? Benchmarking Crowd-Level Reaction Reconstruction with ConsumerSimBench

    cs.CL 2026-05 unverdicted novelty 7.0 of 10

    ConsumerSimBench evaluates 13 LLMs on reconstructing crowd reactions from 1,553 Chinese social-media topics using 23,122 auditable yes-no criteria, finding maximum coverage of 47.8% by Gemini-3.1-Pro.

  2. Beyond Generative Decoding: Discriminative Hidden-State Readout from a Native Omni-Modal LLM for Multimodal Sentiment Analysis

    cs.MM 2026-06 unverdicted novelty 6.0 of 10

    Discriminative readout from the last hidden state of Qwen2.5-Omni-7B outperforms generative decoding for multimodal sentiment regression on MOSI and MOSEI while using far less compute.

  3. EmoScene: A Dual-space Dataset for Controllable Affective Image Generation

    cs.CV 2026-04 reject novelty 6.0 of 10

    EmoScene contributes 1.2M images annotated with discrete emotions, continuous VAD scores, perceptual attributes, and captions, plus a cross-attention modulation that shifts generated images toward requested affective targets.

  4. MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue

    cs.CL 2026-03 unverdicted novelty 6.0 of 10

    MICA combines incremental per-turn distance rewards and Monte Carlo returns from a shared potential function over user support states to create a mixed advantage signal that enables stable multi-turn RL optimization f...

  5. MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue

    cs.CL 2026-03 conditional novelty 5.0 of 10

    MICA mixes per-turn and whole-trajectory normalized reward signals to train emotional-support chatbots, outperforming GRPO and REINFORCE++ on EMPA, EQ-Bench, and EmoBench.

  6. Recent Advances in Multimodal Affective Computing: An NLP Perspective

    cs.CL 2024-09 unverdicted novelty 3.0 of 10

    Survey organizing multimodal affective computing research around four NLP tasks, method paradigms, datasets, evaluation protocols, and future directions while releasing a resource repository.

  7. Intelligent Agents with Emotional Intelligence: Current Trends, Challenges, and Future Prospects

    cs.HC 2025-10 unverdicted novelty 2.0 of 10

    A holistic survey of affective computing for intelligent agents covering emotion understanding via multimodal data, affective cognition, emotional expression synthesis, key challenges, and future directions emphasizin...

Pith tools